[ { "id": "92cb86c259", "title": "A Comparison of Image Processing Techniques for Visual Speech Recognition Applications", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f31b20466ae89669f9741e047487eb37-Abstract.html", "author": "Michael S. Gray; Terrence J. Sejnowski; Javier R. Movellan", "abstract": "We examine eight different techniques for developing visual rep(cid:173) resentations in machine vision tasks. In particular we compare different versions of principal component and independent com(cid:173) ponent analysis in combination with stepwise regression methods for variable selection. We found that local methods, based on the statistics of image patches, consistently outperformed global meth(cid:173) ods based on the statistics of entire images. This result is consistent with previous work on emotion and facial expression recognition. In addition, the use of a stepwise regression technique for selecting variables and regions of interest substantially boosted performance.", "bibtex": "@inproceedings{NIPS2000_f31b2046,\n author = {Gray, Michael and Sejnowski, Terrence J and Movellan, Javier},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A Comparison of Image Processing Techniques for Visual Speech Recognition Applications},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f31b20466ae89669f9741e047487eb37-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f31b20466ae89669f9741e047487eb37-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f31b20466ae89669f9741e047487eb37-Metadata.json", "review": "", "metareview": "", "pdf_size": 1351412, "gs_citation": 8, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=5268427369488776798&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 5, "aff": "Computational Neurobiology Laboratory, The Salk Institute, San Diego, CA 92186-5800; Computational Neurobiology Laboratory, The Salk Institute, San Diego, CA 92186-5800; Department of Cognitive Science, Institute for Neural Computation, University of California San Diego", "aff_domain": ";;", "email": ";;", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;1", "aff_unique_norm": "Salk Institute;University of California, San Diego", "aff_unique_dep": "Computational Neurobiology Laboratory;Department of Cognitive Science, Institute for Neural Computation", "aff_unique_url": "https://www.salk.edu;https://ucsd.edu", "aff_unique_abbr": "Salk Institute;UCSD", "aff_campus_unique_index": "0;0;0", "aff_campus_unique": "San Diego", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "c6fc8a6847", "title": "A Gradient-Based Boosting Algorithm for Regression Problems", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/8d9fc2308c8f28d2a7d2f6f48801c705-Abstract.html", "author": "Richard S. Zemel; Toniann Pitassi", "abstract": "In adaptive boosting, several weak learners trained sequentially are combined to boost the overall algorithm performance. Re(cid:173) cently adaptive boosting methods for classification problems have been derived as gradient descent algorithms. This formulation jus(cid:173) tifies key elements and parameters in the methods, all chosen to optimize a single common objective function. We propose an anal(cid:173) ogous formulation for adaptive boosting of regression problems, utilizing a novel objective function that leads to a simple boosting algorithm. We prove that this method reduces training error, and compare its performance to other regression methods.", "bibtex": "@inproceedings{NIPS2000_8d9fc230,\n author = {Zemel, Richard and Pitassi, Toniann},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A Gradient-Based Boosting Algorithm for Regression Problems},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/8d9fc2308c8f28d2a7d2f6f48801c705-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/8d9fc2308c8f28d2a7d2f6f48801c705-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/8d9fc2308c8f28d2a7d2f6f48801c705-Metadata.json", "review": "", "metareview": "", "pdf_size": 1392233, "gs_citation": 189, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=14816448871288027992&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 19, "aff": "Department of Computer Science, University of Toronto; Department of Computer Science, University of Toronto", "aff_domain": ";", "email": ";", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "University of Toronto", "aff_unique_dep": "Department of Computer Science", "aff_unique_url": "https://www.utoronto.ca", "aff_unique_abbr": "U of T", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Toronto", "aff_country_unique_index": "0;0", "aff_country_unique": "Canada" }, { "id": "670145be83", "title": "A Linear Programming Approach to Novelty Detection", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/0e087ec55dcbe7b2d7992d6b69b519fb-Abstract.html", "author": "Colin Campbell; Kristin P. Bennett", "abstract": "Novelty detection involves modeling the normal behaviour of a sys(cid:173) tem hence enabling detection of any divergence from normality. It has potential applications in many areas such as detection of ma(cid:173) chine damage or highlighting abnormal features in medical data. One approach is to build a hypothesis estimating the support of the normal data i.e. constructing a function which is positive in the region where the data is located and negative elsewhere. Recently kernel methods have been proposed for estimating the support of a distribution and they have performed well in practice - training involves solution of a quadratic programming problem. In this pa(cid:173) per we propose a simpler kernel method for estimating the support based on linear programming. The method is easy to implement and can learn large datasets rapidly. We demonstrate the method on medical and fault detection datasets.", "bibtex": "@inproceedings{NIPS2000_0e087ec5,\n author = {Campbell, Colin and Bennett, Kristin},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A Linear Programming Approach to Novelty Detection},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/0e087ec55dcbe7b2d7992d6b69b519fb-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/0e087ec55dcbe7b2d7992d6b69b519fb-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/0e087ec55dcbe7b2d7992d6b69b519fb-Metadata.json", "review": "", "metareview": "", "pdf_size": 1134452, "gs_citation": 304, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=17294103283395164575&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 14, "aff": "Dept. of Engineering Mathematics, Bristol University, Bristol, BS8 1 TR, United Kingdon; Dept. of Mathematical Sciences, Rensselaer Polytechnic Institute, Troy, New York 12180-3590, United States", "aff_domain": "bris.ac.uk;rpi.edu", "email": "bris.ac.uk;rpi.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Bristol University;Rensselaer Polytechnic Institute", "aff_unique_dep": "Dept. of Engineering Mathematics;Dept. of Mathematical Sciences", "aff_unique_url": "https://www.bristol.ac.uk;https://www.rpi.edu", "aff_unique_abbr": "Bristol;RPI", "aff_campus_unique_index": "0;1", "aff_campus_unique": "Bristol;Troy", "aff_country_unique_index": "0;1", "aff_country_unique": "United Kingdom;United States" }, { "id": "fa95f31ab6", "title": "A Mathematical Programming Approach to the Kernel Fisher Algorithm", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/29530de21430b7540ec3f65135f7323c-Abstract.html", "author": "Sebastian Mika; Gunnar R\u00e4tsch; Klaus-Robert M\u00fcller", "abstract": "We investigate a new kernel-based classifier: the Kernel Fisher Discrim(cid:173) inant (KFD). A mathematical programming formulation based on the ob(cid:173) servation that KFD maximizes the average margin permits an interesting modification of the original KFD algorithm yielding the sparse KFD. We find that both, KFD and the proposed sparse KFD, can be understood in an unifying probabilistic context. Furthermore, we show connections to Support Vector Machines and Relevance Vector Machines. From this understanding, we are able to outline an interesting kernel-regression technique based upon the KFD algorithm. Simulations support the use(cid:173) fulness of our approach.", "bibtex": "@inproceedings{NIPS2000_29530de2,\n author = {Mika, Sebastian and R\\\"{a}tsch, Gunnar and M\\\"{u}ller, Klaus-Robert},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A Mathematical Programming Approach to the Kernel Fisher Algorithm},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/29530de21430b7540ec3f65135f7323c-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/29530de21430b7540ec3f65135f7323c-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/29530de21430b7540ec3f65135f7323c-Metadata.json", "review": "", "metareview": "", "pdf_size": 1419227, "gs_citation": 254, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=18165570964763699102&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 17, "aff": "GMD FIRST.lDA; GMD FIRST.lDA + University of Potsdam; GMD FIRST.lDA + University of Potsdam", "aff_domain": "jirst.gmd.de;jirst.gmd.de;jirst.gmd.de", "email": "jirst.gmd.de;jirst.gmd.de;jirst.gmd.de", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0+1;0+1", "aff_unique_norm": "Global Modeling and Data Assimilation;University of Potsdam", "aff_unique_dep": ";", "aff_unique_url": ";https://www.uni-potsdam.de", "aff_unique_abbr": ";UP", "aff_campus_unique_index": ";", "aff_campus_unique": "", "aff_country_unique_index": "0;0+1;0+1", "aff_country_unique": "China;Germany" }, { "id": "66790bbd8a", "title": "A Neural Probabilistic Language Model", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/728f206c2a01bf572b5940d7d9a8fa4c-Abstract.html", "author": "Yoshua Bengio; R\u00e9jean Ducharme; Pascal Vincent", "abstract": "A goal of statistical language modeling is to learn the joint probability function of sequences of words. This is intrinsically difficult because of the curse of dimensionality: we propose to fight it with its own weapons. In the proposed approach one learns simultaneously (1) a distributed rep(cid:173) resentation for each word (i.e. a similarity between words) along with (2) the probability function for word sequences, expressed with these repre(cid:173) sentations. Generalization is obtained because a sequence of words that has never been seen before gets high probability if it is made of words that are similar to words forming an already seen sentence. We report on experiments using neural networks for the probability function, showing on two text corpora that the proposed approach very significantly im(cid:173) proves on a state-of-the-art trigram model.", "bibtex": "@inproceedings{NIPS2000_728f206c,\n author = {Bengio, Yoshua and Ducharme, R\\'{e}jean and Vincent, Pascal},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A Neural Probabilistic Language Model},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/728f206c2a01bf572b5940d7d9a8fa4c-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/728f206c2a01bf572b5940d7d9a8fa4c-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/728f206c2a01bf572b5940d7d9a8fa4c-Metadata.json", "review": "", "metareview": "", "pdf_size": 1559925, "gs_citation": 12414, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11929840984668291800&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 62, "aff": "Departement d'Informatique et Recherche Operationnelle+Centre de Recherche Mathematiques+Universite de Montreal; Departement d'Informatique et Recherche Operationnelle+Centre de Recherche Mathematiques+Universite de Montreal; Departement d'Informatique et Recherche Operationnelle+Centre de Recherche Mathematiques+Universite de Montreal", "aff_domain": "iro.umontreal.ca;iro.umontreal.ca;iro.umontreal.ca", "email": "iro.umontreal.ca;iro.umontreal.ca;iro.umontreal.ca", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0+1+2;0+1+2;0+1+2", "aff_unique_norm": "Universite de Montreal;Centre de Recherche Mathematiques;Universit\u00e9 de Montr\u00e9al", "aff_unique_dep": "Departement d'Informatique et Recherche Operationnelle;;", "aff_unique_url": "https://www.umontreal.ca;https://crm.math.uottawa.ca/;https://www.umontreal.ca", "aff_unique_abbr": "UM;;UM", "aff_campus_unique_index": ";;", "aff_campus_unique": "", "aff_country_unique_index": "0+0+0;0+0+0;0+0+0", "aff_country_unique": "Canada" }, { "id": "3150fc64ec", "title": "A New Approximate Maximal Margin Classification Algorithm", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/d072677d210ac4c03ba046120f0802ec-Abstract.html", "author": "Claudio Gentile", "abstract": "A new incremental learning algorithm is described which approximates the maximal margin hyperplane w.r.t. norm p ~ 2 for a set of linearly separable data. Our algorithm, called ALMAp (Approximate Large Mar- gin algorithm w.r.t. norm p), takes 0 ((P~21;;2) corrections to sepa(cid:173) rate the data with p-norm margin larger than (1 - 0:) ,,(, where,,( is the p-norm margin of the data and X is a bound on the p-norm of the in(cid:173) stances. ALMAp avoids quadratic (or higher-order) programming meth(cid:173) ods. It is very easy to implement and is as fast as on-line algorithms, such as Rosenblatt's perceptron. We report on some experiments comparing ALMAp to two incremental algorithms: Perceptron and Li and Long's ROMMA. Our algorithm seems to perform quite better than both. The accuracy levels achieved by ALMAp are slightly inferior to those obtained by Support vector Machines (SVMs). On the other hand, ALMAp is quite faster and easier to implement than standard SVMs training algorithms.", "bibtex": "@inproceedings{NIPS2000_d072677d,\n author = {Gentile, Claudio},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A New Approximate Maximal Margin Classification Algorithm},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/d072677d210ac4c03ba046120f0802ec-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/d072677d210ac4c03ba046120f0802ec-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/d072677d210ac4c03ba046120f0802ec-Metadata.json", "review": "", "metareview": "", "pdf_size": 1408819, "gs_citation": 356, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11562612369852459017&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 23, "aff": "DSI, Universita' di Milano", "aff_domain": "dsi.unimi.it", "email": "dsi.unimi.it", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "Universita' di Milano", "aff_unique_dep": "DSI", "aff_unique_url": "https://www.unimi.it", "aff_unique_abbr": "UniMi", "aff_country_unique_index": "0", "aff_country_unique": "Italy" }, { "id": "7d7fba0bad", "title": "A New Model of Spatial Representation in Multimodal Brain Areas", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/d757719ed7c2b66dd17dcee2a3cb29f4-Abstract.html", "author": "Sophie Den\u00e8ve; Jean-Ren\u00e9 Duhamel; Alexandre Pouget", "abstract": "Most models of spatial representations in the cortex assume cells with limited receptive fields that are defined in a particular egocen(cid:173) tric frame of reference. However, cells outside of primary sensory cortex are either gain modulated by postural input or partially shifting. We show that solving classical spatial tasks, like sen(cid:173) sory prediction, multi-sensory integration, sensory-motor transfor(cid:173) mation and motor control requires more complicated intermediate representations that are not invariant in one frame of reference. We present an iterative basis function map that performs these spatial tasks optimally with gain modulated and partially shifting units, and tests it against neurophysiological and neuropsycholog(cid:173) ical data.", "bibtex": "@inproceedings{NIPS2000_d757719e,\n author = {Den\\`{e}ve, Sophie and Duhamel, Jean-Ren\\'{e} and Pouget, Alexandre},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A New Model of Spatial Representation in Multimodal Brain Areas},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/d757719ed7c2b66dd17dcee2a3cb29f4-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/d757719ed7c2b66dd17dcee2a3cb29f4-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/d757719ed7c2b66dd17dcee2a3cb29f4-Metadata.json", "review": "", "metareview": "", "pdf_size": 1403478, "gs_citation": 1, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=13779964516467537429&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 6, "aff": "Department of Brain and Cognitive Science, University of Rochester, Rochester, NY 14620; Institut des Sciences Cognitives, C.N.R.S, Bron, France 69675; Department of Brain and Cognitive, University of Rochester, Rochester, NY 14620", "aff_domain": "bcs.rochester.edu;isc.cnrs\u00b7fr;bcs.rochester.edu", "email": "bcs.rochester.edu;isc.cnrs\u00b7fr;bcs.rochester.edu", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;1;0", "aff_unique_norm": "University of Rochester;Institut des Sciences Cognitives", "aff_unique_dep": "Department of Brain and Cognitive Science;C.N.R.S", "aff_unique_url": "https://www.rochester.edu;", "aff_unique_abbr": "U of R;", "aff_campus_unique_index": "0;1;0", "aff_campus_unique": "Rochester;Bron", "aff_country_unique_index": "0;1;0", "aff_country_unique": "United States;France" }, { "id": "489acab09d", "title": "A PAC-Bayesian Margin Bound for Linear Classifiers: Why SVMs work", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/06a15eb1c3836723b53e4abca8d9b879-Abstract.html", "author": "Ralf Herbrich; Thore Graepel", "abstract": "We present a bound on the generalisation error of linear classifiers in terms of a refined margin quantity on the training set. The result is obtained in a PAC- Bayesian framework and is based on geometrical arguments in the space of linear classifiers. The new bound constitutes an exponential improvement of the so far tightest margin bound by Shawe-Taylor et al. [8] and scales logarithmically in the inverse margin. Even in the case of less training examples than input dimensions sufficiently large margins lead to non-trivial bound values and - plexity term. Furthermore, the classical margin is too coarse a measure for the essential quantity that controls the generalisation error: the volume ratio between the whole hypothesis space and the subset of consistent hypotheses. The practical relevance of the result lies in the fact that the well-known support vector machine is optimal w.r.t. the new bound only if the feature vectors are all of the same length. As a consequence we recommend to use SVMs on normalised feature vectors only - a recommendation that is well supported by our numerical experiments on two benchmark data sets.", "bibtex": "@inproceedings{NIPS2000_06a15eb1,\n author = {Herbrich, Ralf and Graepel, Thore},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A PAC-Bayesian Margin Bound for Linear Classifiers: Why SVMs work},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/06a15eb1c3836723b53e4abca8d9b879-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/06a15eb1c3836723b53e4abca8d9b879-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/06a15eb1c3836723b53e4abca8d9b879-Metadata.json", "review": "", "metareview": "", "pdf_size": 1300073, "gs_citation": 96, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=14929271781961517691&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 10, "aff": "Statistics Research Group Computer Science Department Technical University of Berlin; Statistics Research Group Computer Science Department Technical University of Berlin", "aff_domain": "cs.tu-berlin.de;cs.tu-berlin.de", "email": "cs.tu-berlin.de;cs.tu-berlin.de", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Technical University of Berlin", "aff_unique_dep": "Computer Science Department", "aff_unique_url": "https://www.tu-berlin.de", "aff_unique_abbr": "TU Berlin", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "Germany" }, { "id": "d3be933d77", "title": "A Productive, Systematic Framework for the Representation of Visual Structure", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/fface8385abbf94b4593a0ed53a0c70f-Abstract.html", "author": "Shimon Edelman; Nathan Intrator", "abstract": "We describe a unified framework for the understanding of struc(cid:173) ture representation in primate vision. A model derived from this framework is shown to be effectively systematic in that it has the ability to interpret and associate together objects that are related through a rearrangement of common \"middle-scale\" parts, repre(cid:173) sented as image fragments. The model addresses the same concerns as previous work on compositional representation through the use of what+where receptive fields and attentional gain modulation. It does not require prior exposure to the individual parts, and avoids the need for abstract symbolic binding.", "bibtex": "@inproceedings{NIPS2000_fface838,\n author = {Edelman, Shimon and Intrator, Nathan},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A Productive, Systematic Framework for the Representation of Visual Structure},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/fface8385abbf94b4593a0ed53a0c70f-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/fface8385abbf94b4593a0ed53a0c70f-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/fface8385abbf94b4593a0ed53a0c70f-Metadata.json", "review": "", "metareview": "", "pdf_size": 1403787, "gs_citation": 23, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=15735320663257172282&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 7, "aff": "Cornell University; Brown University", "aff_domain": "cornell.edu;brown.edu", "email": "cornell.edu;brown.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Cornell University;Brown University", "aff_unique_dep": ";", "aff_unique_url": "https://www.cornell.edu;https://www.brown.edu", "aff_unique_abbr": "Cornell;Brown", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "6f5b3adbf6", "title": "A Silicon Primitive for Competitive Learning", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/73e0f7487b8e5297182c5a711d20bf26-Abstract.html", "author": "David Hsu; Miguel Figueroa; Chris Diorio", "abstract": "Competitive learning is a technique for training classification and clustering networks. We have designed and fabricated an 11- transistor primitive, that we term an automaximizing bump circuit, that implements competitive learning dynamics. The circuit per(cid:173) forms a similarity computation, affords nonvolatile storage, and implements simultaneous local adaptation and computation. We show that our primitive is suitable for implementing competitive learning in VLSI, and demonstrate its effectiveness in a standard clustering task.", "bibtex": "@inproceedings{NIPS2000_73e0f748,\n author = {Hsu, David and Figueroa, Miguel and Diorio, Chris},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A Silicon Primitive for Competitive Learning},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/73e0f7487b8e5297182c5a711d20bf26-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/73e0f7487b8e5297182c5a711d20bf26-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/73e0f7487b8e5297182c5a711d20bf26-Metadata.json", "review": "", "metareview": "", "pdf_size": 1308421, "gs_citation": 15, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=5112432026524314154&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 11, "aff": "Computer Science and Engineering, The University of Washington; Computer Science and Engineering, The University of Washington; Computer Science and Engineering, The University of Washington", "aff_domain": "cs.washington.edu;cs.washington.edu;cs.washington.edu", "email": "cs.washington.edu;cs.washington.edu;cs.washington.edu", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0", "aff_unique_norm": "University of Washington", "aff_unique_dep": "Computer Science and Engineering", "aff_unique_url": "https://www.washington.edu", "aff_unique_abbr": "UW", "aff_campus_unique_index": "0;0;0", "aff_campus_unique": "Seattle", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "937f9241be", "title": "A Support Vector Method for Clustering", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/14cfdb59b5bda1fc245aadae15b1984a-Abstract.html", "author": "Asa Ben-Hur; David Horn; Hava T. Siegelmann; Vladimir Vapnik", "abstract": "We present a novel method for clustering using the support vector ma(cid:173) chine approach. Data points are mapped to a high dimensional feature space, where support vectors are used to define a sphere enclosing them. The boundary of the sphere forms in data space a set of closed contours containing the data. Data points enclosed by each contour are defined as a cluster. As the width parameter of the Gaussian kernel is decreased, these contours fit the data more tightly and splitting of contours occurs. The algorithm works by separating clusters according to valleys in the un(cid:173) derlying probability distribution, and thus clusters can take on arbitrary geometrical shapes. As in other SV algorithms, outliers can be dealt with by introducing a soft margin constant leading to smoother cluster bound(cid:173) aries. The structure of the data is explored by varying the two parame(cid:173) ters. We investigate the dependence of our method on these parameters and apply it to several data sets.", "bibtex": "@inproceedings{NIPS2000_14cfdb59,\n author = {Ben-Hur, Asa and Horn, David and Siegelmann, Hava and Vapnik, Vladimir},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A Support Vector Method for Clustering},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/14cfdb59b5bda1fc245aadae15b1984a-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/14cfdb59b5bda1fc245aadae15b1984a-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/14cfdb59b5bda1fc245aadae15b1984a-Metadata.json", "review": "", "metareview": "", "pdf_size": 1182727, "gs_citation": 18, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=6813149741804351883&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 20, "aff": ";;;", "aff_domain": ";;;", "email": ";;;", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster" }, { "id": "362aca58be", "title": "A Tighter Bound for Graphical Models", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/07a4e20a7bbeeb7a736682b26b16ebe8-Abstract.html", "author": "Martijn A. R. Leisink; Hilbert J. Kappen", "abstract": "We present a method to bound the partition function of a Boltz(cid:173) mann machine neural network with any odd order polynomial. This is a direct extension of the mean field bound, which is first order. We show that the third order bound is strictly better than mean field. Additionally we show the rough outline how this bound is applicable to sigmoid belief networks. Numerical experiments in(cid:173) dicate that an error reduction of a factor two is easily reached in the region where expansion based approximations are useful.", "bibtex": "@inproceedings{NIPS2000_07a4e20a,\n author = {Leisink, Martijn and Kappen, Hilbert},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A Tighter Bound for Graphical Models},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/07a4e20a7bbeeb7a736682b26b16ebe8-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/07a4e20a7bbeeb7a736682b26b16ebe8-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/07a4e20a7bbeeb7a736682b26b16ebe8-Metadata.json", "review": "", "metareview": "", "pdf_size": 1157209, "gs_citation": 31, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=1692653594352549006&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 17, "aff": "University of Nijmegen, Department of Biophysics; University of Nijmegen, Department of Biophysics", "aff_domain": "mbfys.kun.nl;mbfys.kun.nl", "email": "mbfys.kun.nl;mbfys.kun.nl", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Radboud University Nijmegen", "aff_unique_dep": "Department of Biophysics", "aff_unique_url": "https://www.ru.nl/", "aff_unique_abbr": "RU", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "Netherlands" }, { "id": "321e9eba01", "title": "A Variational Mean-Field Theory for Sigmoidal Belief Networks", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/e74c0d42b4433905293aab661fcf8ddb-Abstract.html", "author": "Chiranjib Bhattacharyya; S. Sathiya Keerthi", "abstract": "A variational derivation of Plefka's mean-field theory is presented. This theory is then applied to sigmoidal belief networks with the aid of further approximations. Empirical evaluation on small scale networks show that the proposed approximations are quite com(cid:173) petitive.", "bibtex": "@inproceedings{NIPS2000_e74c0d42,\n author = {Bhattacharyya, Chiranjib and Keerthi, S.},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {A Variational Mean-Field Theory for Sigmoidal Belief Networks},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/e74c0d42b4433905293aab661fcf8ddb-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/e74c0d42b4433905293aab661fcf8ddb-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/e74c0d42b4433905293aab661fcf8ddb-Metadata.json", "review": "", "metareview": "", "pdf_size": 991503, "gs_citation": 1, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=6369805194977368240&as_sdt=400005&sciodt=0,14&hl=en", "gs_version_total": 5, "aff": "Computer Science and Automation, Indian Institute of Science, Bangalore, India, 560012; Mechanical and Production Engineering, National University of Singapore", "aff_domain": "csa.iisc.ernet.in;guppy.mpe.nus.edu.sg", "email": "csa.iisc.ernet.in;guppy.mpe.nus.edu.sg", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Indian Institute of Science;National University of Singapore", "aff_unique_dep": "Computer Science and Automation;Mechanical and Production Engineering", "aff_unique_url": "https://www.iisc.ac.in;https://www.nus.edu.sg", "aff_unique_abbr": "IISc;NUS", "aff_campus_unique_index": "0", "aff_campus_unique": "Bangalore;", "aff_country_unique_index": "0;1", "aff_country_unique": "India;Singapore" }, { "id": "659fb0bd87", "title": "APRICODD: Approximate Policy Construction Using Decision Diagrams", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/201d7288b4c18a679e48b31c72c30ded-Abstract.html", "author": "Robert St-Aubin; Jesse Hoey; Craig Boutilier", "abstract": "We propose a method of approximate dynamic programming for Markov decision processes (MDPs) using algebraic decision diagrams (ADDs). We produce near-optimal value functions and policies with much lower time and space requirements than exact dynamic programming. Our method reduces the sizes of the intermediate value functions generated during value iteration by replacing the values at the terminals of the ADD with ranges of values. Our method is demonstrated on a class of large MDPs (with up to 34 billion states), and we compare the results with the optimal value functions.", "bibtex": "@inproceedings{NIPS2000_201d7288,\n author = {St-Aubin, Robert and Hoey, Jesse and Boutilier, Craig},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {APRICODD: Approximate Policy Construction Using Decision Diagrams},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/201d7288b4c18a679e48b31c72c30ded-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/201d7288b4c18a679e48b31c72c30ded-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/201d7288b4c18a679e48b31c72c30ded-Metadata.json", "review": "", "metareview": "", "pdf_size": 1341787, "gs_citation": 191, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=7697642699957999815&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 23, "aff": "Dept. of Computer Science, University of British Columbia; Dept. of Computer Science, University of British Columbia; Dept. of Computer Science, University of Toronto", "aff_domain": "cs.ubc.ca;cs.ubc.ca;cs.toronto.edu", "email": "cs.ubc.ca;cs.ubc.ca;cs.toronto.edu", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;1", "aff_unique_norm": "University of British Columbia;University of Toronto", "aff_unique_dep": "Department of Computer Science;Department of Computer Science", "aff_unique_url": "https://www.ubc.ca;https://www.utoronto.ca", "aff_unique_abbr": "UBC;U of T", "aff_campus_unique_index": "0;0;1", "aff_campus_unique": "Vancouver;Toronto", "aff_country_unique_index": "0;0;0", "aff_country_unique": "Canada" }, { "id": "76330538c5", "title": "Accumulator Networks: Suitors of Local Probability Propagation", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/537de305e941fccdbba5627e3eefbb24-Abstract.html", "author": "Brendan J. Frey; Anitha Kannan", "abstract": "One way to approximate inference in richly-connected graphical models is to apply the sum-product algorithm (a.k.a. probabil(cid:173) ity propagation algorithm), while ignoring the fact that the graph has cycles. The sum-product algorithm can be directly applied in Gaussian networks and in graphs for coding, but for many condi(cid:173) tional probability functions - including the sigmoid function - di(cid:173) rect application of the sum-product algorithm is not possible. We introduce \"accumulator networks\" that have low local complexity (but exponential global complexity) so the sum-product algorithm can be directly applied. In an accumulator network, the probability of a child given its parents is computed by accumulating the inputs from the parents in a Markov chain or more generally a tree. After giving expressions for inference and learning in accumulator net(cid:173) works, we give results on the \"bars problem\" and on the problem of extracting translated, overlapping faces from an image.", "bibtex": "@inproceedings{NIPS2000_537de305,\n author = {Frey, Brendan J and Kannan, Anitha},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Accumulator Networks: Suitors of Local Probability Propagation},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/537de305e941fccdbba5627e3eefbb24-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/537de305e941fccdbba5627e3eefbb24-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/537de305e941fccdbba5627e3eefbb24-Metadata.json", "review": "", "metareview": "", "pdf_size": 1436977, "gs_citation": 7, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=15494164000574464324&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 5, "aff": ";", "aff_domain": ";", "email": ";", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster" }, { "id": "f3233fe444", "title": "Active Inference in Concept Learning", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/15d185eaa7c954e77f5343d941e25fbd-Abstract.html", "author": "Jonathan D. Nelson; Javier R. Movellan", "abstract": "People are active experimenters, not just passive observers, constantly seeking new information relevant to their goals. A reasonable approach to active information gathering is to ask questions and conduct experiments that maximize the expected information gain, given current beliefs (Fedorov 1972, MacKay 1992, Oaksford & Chater 1994). In this paper we present results on an exploratory experiment designed to study people's active information gathering behavior on a concept task (Tenenbaum 2000). The results of the experiment are analyzed in terms of the expected information gain of the questions asked by subjects.", "bibtex": "@inproceedings{NIPS2000_15d185ea,\n author = {Nelson, Jonathan and Movellan, Javier},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Active Inference in Concept Learning},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/15d185eaa7c954e77f5343d941e25fbd-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/15d185eaa7c954e77f5343d941e25fbd-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/15d185eaa7c954e77f5343d941e25fbd-Metadata.json", "review": "", "metareview": "", "pdf_size": 1340512, "gs_citation": 51, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=991944891335579775&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 16, "aff": "Department of Cognitive Science, University of California, San Diego; Department of Cognitive Science, University of California, San Diego", "aff_domain": "cogsci.ucsd.edu;inc.ucsd.edu", "email": "cogsci.ucsd.edu;inc.ucsd.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "University of California, San Diego", "aff_unique_dep": "Department of Cognitive Science", "aff_unique_url": "https://ucsd.edu", "aff_unique_abbr": "UCSD", "aff_campus_unique_index": "0;0", "aff_campus_unique": "San Diego", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "16cf82281d", "title": "Active Learning for Parameter Estimation in Bayesian Networks", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/0731460a8a5ce1626210cbf4385ae0ef-Abstract.html", "author": "Simon Tong; Daphne Koller", "abstract": "Bayesian networks are graphical representations of probability distributions. In virtually all of the work on learning these networks, the assumption is that we are presented with a data set consisting of randomly generated instances from the underlying distribution. In many situations, however, we also have the option of active learning, where we have the possibility of guiding the sampling process by querying for certain types of samples. This paper addresses the problem of estimating the parameters of Bayesian networks in an active learning setting. We provide a theoretical framework for this problem, and an algorithm that chooses which active learning queries to generate based on the model learned so far. We present experimental results showing that our active learning algorithm can significantly reduce the need for training data in many situations.", "bibtex": "@inproceedings{NIPS2000_0731460a,\n author = {Tong, Simon and Koller, Daphne},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Active Learning for Parameter Estimation in Bayesian Networks},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/0731460a8a5ce1626210cbf4385ae0ef-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/0731460a8a5ce1626210cbf4385ae0ef-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/0731460a8a5ce1626210cbf4385ae0ef-Metadata.json", "review": "", "metareview": "", "pdf_size": 1629580, "gs_citation": 212, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=6707808370500984509&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 10, "aff": "Computer Science Department, Stanford University; Computer Science Department, Stanford University", "aff_domain": "cs.stanford.edu;cs.stanford.edu", "email": "cs.stanford.edu;cs.stanford.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Stanford University", "aff_unique_dep": "Computer Science Department", "aff_unique_url": "https://www.stanford.edu", "aff_unique_abbr": "Stanford", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Stanford", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "54f339d6ba", "title": "Active Support Vector Machine Classification", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/b139e104214a08ae3f2ebcce149cdf6e-Abstract.html", "author": "Olvi L. Mangasarian; David R. Musicant", "abstract": "An active set strategy is applied to the dual of a simple reformula(cid:173) tion of the standard quadratic program of a linear support vector machine. This application generates a fast new dual algorithm that consists of solving a finite number of linear equations, with a typically large dimensionality equal to the number of points to be classified. However, by making novel use of the Sherman-Morrison(cid:173) Woodbury formula, a much smaller matrix of the order of the orig(cid:173) inal input space is inverted at each step. Thus, a problem with a 32-dimensional input space and 7 million points required inverting positive definite symmetric matrices of size 33 x 33 with a total run(cid:173) ning time of 96 minutes on a 400 MHz Pentium II. The algorithm requires no specialized quadratic or linear programming code, but merely a linear equation solver which is publicly available.", "bibtex": "@inproceedings{NIPS2000_b139e104,\n author = {Mangasarian, Olvi and Musicant, David},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Active Support Vector Machine Classification},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/b139e104214a08ae3f2ebcce149cdf6e-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/b139e104214a08ae3f2ebcce149cdf6e-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/b139e104214a08ae3f2ebcce149cdf6e-Metadata.json", "review": "", "metareview": "", "pdf_size": 1436312, "gs_citation": 209, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=16072836986605341773&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 10, "aff": "Computer Sciences Dept., University of Wisconsin; Dept. of Mathematics and Computer Science, Carleton College", "aff_domain": "cs.wisc.edu;carleton.edu", "email": "cs.wisc.edu;carleton.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "University of Wisconsin;Carleton College", "aff_unique_dep": "Computer Sciences Dept.;Dept. of Mathematics and Computer Science", "aff_unique_url": "https://www.wisc.edu;https://www.carleton.edu", "aff_unique_abbr": "UW;Carleton", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "7c0d1ea2d9", "title": "Adaptive Object Representation with Hierarchically-Distributed Memory Sites", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/68148596109e38cf9367d27875e185be-Abstract.html", "author": "Bosco S. Tjan", "abstract": "Theories of object recognition often assume that only one representa(cid:173) tion scheme is used within one visual-processing pathway. Versatility of the visual system comes from having multiple visual-processing pathways, each specialized in a different category of objects. We propose a theoretically simpler alternative, capable of explaining the same set of data and more. A single primary visual-processing pathway, loosely modular, is assumed. Memory modules are attached to sites along this pathway. Object-identity decision is made independently at each site. A site's response time is a monotonic-decreasing function of its confidence regarding its decision. An observer's response is the first-arriving response from any site. The effective representation(s) of such a system, determined empirically, can appear to be specialized for different tasks and stimuli, consistent with recent clinical and functional-imaging findings. This, however, merely reflects a decision being made at its appropriate level of abstraction. The system itself is intrinsically flexible and adaptive.", "bibtex": "@inproceedings{NIPS2000_68148596,\n author = {Tjan, Bosco},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Adaptive Object Representation with Hierarchically-Distributed Memory Sites},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/68148596109e38cf9367d27875e185be-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/68148596109e38cf9367d27875e185be-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/68148596109e38cf9367d27875e185be-Metadata.json", "review": "", "metareview": "", "pdf_size": 1381392, "gs_citation": 17, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11774968978150070473&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 9, "aff": "Department of Psychology, University of Southern California", "aff_domain": "usc.edu", "email": "usc.edu", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "University of Southern California", "aff_unique_dep": "Department of Psychology", "aff_unique_url": "https://www.usc.edu", "aff_unique_abbr": "USC", "aff_campus_unique_index": "0", "aff_campus_unique": "Los Angeles", "aff_country_unique_index": "0", "aff_country_unique": "United States" }, { "id": "162d8d7017", "title": "Algebraic Information Geometry for Learning Machines with Singularities", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f442d33fa06832082290ad8544a8da27-Abstract.html", "author": "Sumio Watanabe", "abstract": "Algebraic geometry is essential to learning theory. In hierarchical learning machines such as layered neural networks and gaussian mixtures, the asymptotic normality does not hold, since Fisher in(cid:173) formation matrices are singular. In this paper , the rigorous asymp(cid:173) totic form of the stochastic complexity is clarified based on resolu(cid:173) tion of singularities and two different problems are studied. (1) If the prior is positive, then the stochastic complexity is far smaller than BIO, resulting in the smaller generalization error than regular statistical models, even when the true distribution is not contained in the parametric model. nate free and equal to zero at singularities, is employed then the stochastic complexity has the same form as BIO. It is useful for model selection, but not for generalization.", "bibtex": "@inproceedings{NIPS2000_f442d33f,\n author = {Watanabe, Sumio},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Algebraic Information Geometry for Learning Machines with Singularities},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f442d33fa06832082290ad8544a8da27-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f442d33fa06832082290ad8544a8da27-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f442d33fa06832082290ad8544a8da27-Metadata.json", "review": "", "metareview": "", "pdf_size": 1108548, "gs_citation": 46, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=6880051537900159593&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 9, "aff": "", "aff_domain": "", "email": "", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster" }, { "id": "b7dc317e32", "title": "Algorithmic Stability and Generalization Performance", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/49ad23d1ec9fa4bd8d77d02681df5cfa-Abstract.html", "author": "Olivier Bousquet; Andr\u00e9 Elisseeff", "abstract": "We present a novel way of obtaining PAC-style bounds on the gen(cid:173) eralization error of learning algorithms, explicitly using their stabil(cid:173) ity properties. A stable learner is one for which the learned solution does not change much with small changes in the training set. The bounds we obtain do not depend on any measure of the complexity of the hypothesis space (e.g. VC dimension) but rather depend on how the learning algorithm searches this space, and can thus be applied even when the VC dimension is infinite. We demonstrate that regularization networks possess the required stability property and apply our method to obtain new bounds on their generalization performance.", "bibtex": "@inproceedings{NIPS2000_49ad23d1,\n author = {Bousquet, Olivier and Elisseeff, Andr\\'{e}},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Algorithmic Stability and Generalization Performance},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/49ad23d1ec9fa4bd8d77d02681df5cfa-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/49ad23d1ec9fa4bd8d77d02681df5cfa-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/49ad23d1ec9fa4bd8d77d02681df5cfa-Metadata.json", "review": "", "metareview": "", "pdf_size": 1231315, "gs_citation": 188, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=12262726464327020970&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 8, "aff": "CMAP Ecole Polytechnique; Barnhill Technologies", "aff_domain": "cmapx.polytechnique.fr;barnhilltechnologies.com", "email": "cmapx.polytechnique.fr;barnhilltechnologies.com", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Ecole Polytechnique;Barnhill Technologies", "aff_unique_dep": "CMAP;", "aff_unique_url": "https://www.polytechnique.edu;", "aff_unique_abbr": "Polytechnique;", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;1", "aff_country_unique": "France;United States" }, { "id": "89f3326db6", "title": "Algorithms for Non-negative Matrix Factorization", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f9d1152547c0bde01830b7e8bd60024c-Abstract.html", "author": "Daniel D. Lee; H. Sebastian Seung", "abstract": "Non-negative matrix factorization (NMF) has previously been shown to \nbe a useful decomposition for multivariate data. Two different multi- \nplicative algorithms for NMF are analyzed. They differ only slightly in \nthe multiplicative factor used in the update rules. One algorithm can be \nshown to minimize the conventional least squares error while the other \nminimizes the generalized Kullback-Leibler divergence. The monotonic \nconvergence of both algorithms can be proven using an auxiliary func- \ntion analogous to that used for proving convergence of the Expectation- \nMaximization algorithm. The algorithms can also be interpreted as diag- \nonally rescaled gradient descent, where the rescaling factor is optimally \nchosen to ensure convergence.", "bibtex": "@inproceedings{NIPS2000_f9d11525,\n author = {Lee, Daniel and Seung, H. Sebastian},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Algorithms for Non-negative Matrix Factorization},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f9d1152547c0bde01830b7e8bd60024c-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f9d1152547c0bde01830b7e8bd60024c-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f9d1152547c0bde01830b7e8bd60024c-Metadata.json", "review": "", "metareview": "", "pdf_size": 1123675, "gs_citation": 12304, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=13475348098649957727&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 25, "aff": "Bell Laboratories, Lucent Technologies, Murray Hill, NJ 07974; Dept. of Brain and Cog. Sci., Massachusetts Institute of Technology, Cambridge, MA 02138", "aff_domain": ";", "email": ";", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Bell Laboratories;Massachusetts Institute of Technology", "aff_unique_dep": ";Department of Brain and Cognitive Sciences", "aff_unique_url": ";https://www.mit.edu", "aff_unique_abbr": ";MIT", "aff_campus_unique_index": "0;1", "aff_campus_unique": "Murray Hill;Cambridge", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "0450204504", "title": "An Adaptive Metric Machine for Pattern Classification", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/7e9e346dc5fd268b49bf418523af8679-Abstract.html", "author": "Carlotta Domeniconi; Jing Peng; Dimitrios Gunopulos", "abstract": "Nearest neighbor classification assumes locally constant class con(cid:173) ditional probabilities. This assumption becomes invalid in high dimensions with finite samples due to the curse of dimensionality. Severe bias can be introduced under these conditions when using the nearest neighbor rule. We propose a locally adaptive nearest neighbor classification method to try to minimize bias. We use a Chi-squared distance analysis to compute a flexible metric for pro(cid:173) ducing neighborhoods that are elongated along less relevant feature dimensions and constricted along most influential ones. As a result, the class conditional probabilities tend to be smoother in the mod(cid:173) ified neighborhoods, whereby better classification performance can be achieved. The efficacy of our method is validated and compared against other techniques using a variety of real world data.", "bibtex": "@inproceedings{NIPS2000_7e9e346d,\n author = {Domeniconi, Carlotta and Peng, Jing and Gunopulos, Dimitrios},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {An Adaptive Metric Machine for Pattern Classification},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/7e9e346dc5fd268b49bf418523af8679-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/7e9e346dc5fd268b49bf418523af8679-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/7e9e346dc5fd268b49bf418523af8679-Metadata.json", "review": "", "metareview": "", "pdf_size": 1388797, "gs_citation": 79, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=5708114452789661606&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 9, "aff": ";;", "aff_domain": ";;", "email": ";;", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster" }, { "id": "c32b9eca61", "title": "An Information Maximization Approach to Overcomplete and Recurrent Representations", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/09fb05dd477d4ae6479985ca56c5a12d-Abstract.html", "author": "Oren Shriki; Haim Sompolinsky; Daniel D. Lee", "abstract": "The principle of maximizing mutual information is applied to learning overcomplete and recurrent representations. The underlying model con(cid:173) sists of a network of input units driving a larger number of output units with recurrent interactions. In the limit of zero noise, the network is de(cid:173) terministic and the mutual information can be related to the entropy of the output units. Maximizing this entropy with respect to both the feed(cid:173) forward connections as well as the recurrent interactions results in simple learning rules for both sets of parameters. The conventional independent components (ICA) learning algorithm can be recovered as a special case where there is an equal number of output units and no recurrent con(cid:173) nections. The application of these new learning rules is illustrated on a simple two-dimensional input example.", "bibtex": "@inproceedings{NIPS2000_09fb05dd,\n author = {Shriki, Oren and Sompolinsky, Haim and Lee, Daniel},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {An Information Maximization Approach to Overcomplete and Recurrent Representations},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/09fb05dd477d4ae6479985ca56c5a12d-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/09fb05dd477d4ae6479985ca56c5a12d-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/09fb05dd477d4ae6479985ca56c5a12d-Metadata.json", "review": "", "metareview": "", "pdf_size": 1065428, "gs_citation": 36, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=3911978194363745867&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 16, "aff": ";;", "aff_domain": ";;", "email": ";;", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster" }, { "id": "48e11189fc", "title": "Analysis of Bit Error Probability of Direct-Sequence CDMA Multiuser Demodulators", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/e5b294b70c9647dcf804d7baa1903918-Abstract.html", "author": "Toshiyuki Tanaka", "abstract": "We analyze the bit error probability of multiuser demodulators for direct(cid:173) sequence binary phase-shift-keying (DSIBPSK) CDMA channel with ad(cid:173) ditive gaussian noise. The problem of multiuser demodulation is cast into the finite-temperature decoding problem, and replica analysis is ap(cid:173) plied to evaluate the performance of the resulting MPM (Marginal Pos(cid:173) terior Mode) demodulators, which include the optimal demodulator and the MAP demodulator as special cases. An approximate implementa(cid:173) tion of demodulators is proposed using analog-valued Hopfield model as a naive mean-field approximation to the MPM demodulators, and its performance is also evaluated by the replica analysis. Results of the per(cid:173) formance evaluation shows effectiveness of the optimal demodulator and the mean-field demodulator compared with the conventional one, espe(cid:173) cially in the cases of small information bit rate and low noise level.", "bibtex": "@inproceedings{NIPS2000_e5b294b7,\n author = {Tanaka, Toshiyuki},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Analysis of Bit Error Probability of Direct-Sequence CDMA Multiuser Demodulators},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/e5b294b70c9647dcf804d7baa1903918-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/e5b294b70c9647dcf804d7baa1903918-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/e5b294b70c9647dcf804d7baa1903918-Metadata.json", "review": "", "metareview": "", "pdf_size": 1024204, "gs_citation": 27, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=4314420830411686173&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 9, "aff": "Department of Electronics and Information Engineering, Tokyo Metropolitan University, Hachioji, Tokyo 192-0397, Japan", "aff_domain": "eeLmetro-u.ac.jp", "email": "eeLmetro-u.ac.jp", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "Tokyo Metropolitan University", "aff_unique_dep": "Department of Electronics and Information Engineering", "aff_unique_url": "https://www.tmuc.ac.jp", "aff_unique_abbr": "TMU", "aff_campus_unique_index": "0", "aff_campus_unique": "Hachioji", "aff_country_unique_index": "0", "aff_country_unique": "Japan" }, { "id": "4a2e425043", "title": "Automated State Abstraction for Options using the U-Tree Algorithm", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/596dedf4498e258e4bdc9fd70df9a859-Abstract.html", "author": "Anders Jonsson; Andrew G. Barto", "abstract": "Part of", "bibtex": "@inproceedings{NIPS2000_596dedf4,\n author = {Jonsson, Anders and Barto, Andrew},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Automated State Abstraction for Options using the U-Tree Algorithm},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/596dedf4498e258e4bdc9fd70df9a859-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/596dedf4498e258e4bdc9fd70df9a859-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/596dedf4498e258e4bdc9fd70df9a859-Metadata.json", "review": "", "metareview": "", "pdf_size": 1378531, "gs_citation": 92, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=6787077985032333888&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 10, "aff": "Department of Computer Science, University of Massachusetts; Department of Computer Science, University of Massachusetts", "aff_domain": "cs.umass.edu;cs.umass.edu", "email": "cs.umass.edu;cs.umass.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "University of Massachusetts", "aff_unique_dep": "Department of Computer Science", "aff_unique_url": "https://www.umass.edu", "aff_unique_abbr": "UMass", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "2b69f8fe7f", "title": "Automatic Choice of Dimensionality for PCA", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/7503cfacd12053d309b6bed5c89de212-Abstract.html", "author": "Thomas P. Minka", "abstract": "A central issue in principal component analysis (PCA) is choosing the number of principal components to be retained. By interpreting PCA as density estimation, we show how to use Bayesian model selection to es(cid:173) timate the true dimensionality of the data. The resulting estimate is sim(cid:173) ple to compute yet guaranteed to pick the correct dimensionality, given enough data. The estimate involves an integral over the Steifel manifold of k-frames, which is difficult to compute exactly. But after choosing an appropriate parameterization and applying Laplace's method, an accu(cid:173) rate and practical estimator is obtained. In simulations, it is convincingly better than cross-validation and other proposed algorithms, plus it runs much faster.", "bibtex": "@inproceedings{NIPS2000_7503cfac,\n author = {Minka, Thomas},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Automatic Choice of Dimensionality for PCA},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/7503cfacd12053d309b6bed5c89de212-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/7503cfacd12053d309b6bed5c89de212-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/7503cfacd12053d309b6bed5c89de212-Metadata.json", "review": "", "metareview": "", "pdf_size": 1117812, "gs_citation": 835, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=2340103223716564652&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 15, "aff": "MIT Media Lab", "aff_domain": "media.mit.edu", "email": "media.mit.edu", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "Massachusetts Institute of Technology", "aff_unique_dep": "Media Lab", "aff_unique_url": "http://www.media.mit.edu/", "aff_unique_abbr": "MIT", "aff_campus_unique_index": "0", "aff_campus_unique": "Cambridge", "aff_country_unique_index": "0", "aff_country_unique": "United States" }, { "id": "5aaa28724e", "title": "Balancing Multiple Sources of Reward in Reinforcement Learning", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/e0ab531ec312161511493b002f9be2ee-Abstract.html", "author": "Christian R. Shelton", "abstract": "For many problems which would be natural for reinforcement learning, the reward signal is not a single scalar value but has multiple scalar com(cid:173) ponents. Examples of such problems include agents with multiple goals and agents with multiple users. Creating a single reward value by com(cid:173) bining the multiple components can throwaway vital information and can lead to incorrect solutions. We describe the multiple reward source problem and discuss the problems with applying traditional reinforce(cid:173) ment learning. We then present an new algorithm for finding a solution and results on simulated environments.", "bibtex": "@inproceedings{NIPS2000_e0ab531e,\n author = {Shelton, Christian},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Balancing Multiple Sources of Reward in Reinforcement Learning},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/e0ab531ec312161511493b002f9be2ee-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/e0ab531ec312161511493b002f9be2ee-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/e0ab531ec312161511493b002f9be2ee-Metadata.json", "review": "", "metareview": "", "pdf_size": 1328965, "gs_citation": 67, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=18213460608677578599&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 19, "aff": "", "aff_domain": "", "email": "", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster" }, { "id": "a12a9acb69", "title": "Bayes Networks on Ice: Robotic Search for Antarctic Meteorites", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/ac5dab2e99eee9cf9ec672e383691302-Abstract.html", "author": "Liam Pedersen; Dimitrios Apostolopoulos; William Whittaker", "abstract": "A Bayes network based classifier for distinguishing terrestrial rocks from meteorites is implemented onboard the Nomad robot. Equipped with a camera, spectrometer and eddy current sensor, this robot searched the ice sheets of Antarctica and autonomously made the first robotic identification of a meteorite, in January 2000 at the Elephant Moraine. This paper discusses rock classification from a robotic platform, and describes the system onboard Nomad.", "bibtex": "@inproceedings{NIPS2000_ac5dab2e,\n author = {Pedersen, Liam and Apostolopoulos, Dimitrios and Whittaker, William},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Bayes Networks on Ice: Robotic Search for Antarctic Meteorites},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/ac5dab2e99eee9cf9ec672e383691302-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/ac5dab2e99eee9cf9ec672e383691302-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/ac5dab2e99eee9cf9ec672e383691302-Metadata.json", "review": "", "metareview": "", "pdf_size": 1214579, "gs_citation": 5, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=1907952133889592513&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 10, "aff": "Robotics Institute, Carnegie Mellon University; Robotics Institute, Carnegie Mellon University; Robotics Institute, Carnegie Mellon University", "aff_domain": "ri.cmu.edu;ri.cmu.edu;ri.cmu.edu", "email": "ri.cmu.edu;ri.cmu.edu;ri.cmu.edu", "github": "", "project": "http://www.cs.cmu.edu/-pedersen", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0", "aff_unique_norm": "Carnegie Mellon University", "aff_unique_dep": "Robotics Institute", "aff_unique_url": "https://www.cmu.edu", "aff_unique_abbr": "CMU", "aff_campus_unique_index": "0;0;0", "aff_campus_unique": "Pittsburgh", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "6bd870e1b6", "title": "Bayesian Video Shot Segmentation", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/5b6ba13f79129a74a3e819b78e36b922-Abstract.html", "author": "Nuno Vasconcelos; Andrew Lippman", "abstract": "Prior knowledge about video structure can be used both as a means to improve the peiformance of content analysis and to extract features that allow semantic classification. We introduce statistical models for two important components of this structure, shot duration and activity, and demonstrate the usefulness of these models by introducing a Bayesian formulation for the shot segmentation problem. The new formulations is shown to extend standard thresholding methods in an adaptive and intuitive way, leading to improved segmentation accuracy.", "bibtex": "@inproceedings{NIPS2000_5b6ba13f,\n author = {Vasconcelos, Nuno and Lippman, Andrew},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Bayesian Video Shot Segmentation},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/5b6ba13f79129a74a3e819b78e36b922-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/5b6ba13f79129a74a3e819b78e36b922-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/5b6ba13f79129a74a3e819b78e36b922-Metadata.json", "review": "", "metareview": "", "pdf_size": 1235724, "gs_citation": 10, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=175983143355983760&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 9, "aff": ";", "aff_domain": ";", "email": ";", "github": "", "project": "http://www.media.mit.edurnuno", "author_num": 2, "track": "main", "status": "Poster" }, { "id": "130aa8bf66", "title": "Beyond Maximum Likelihood and Density Estimation: A Sample-Based Criterion for Unsupervised Learning of Complex Models", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/6e79ed05baec2754e25b4eac73a332d2-Abstract.html", "author": "Sepp Hochreiter; Michael Mozer", "abstract": "The goal of many unsupervised learning procedures is to bring two probability distributions into alignment. Generative models such as Gaussian mixtures and Boltzmann machines can be cast in this light, as can recoding models such as ICA and projection pursuit. We propose a novel sample-based error measure for these classes of models, which applies even in situations where maximum likelihood (ML) and probability density estimation-based formulations can(cid:173) not be applied, e.g., models that are nonlinear or have intractable posteriors. Furthermore, our sample-based error measure avoids the difficulties of approximating a density function. We prove that with an unconstrained model, (1) our approach converges on the correct solution as the number of samples goes to infinity, and (2) the expected solution of our approach in the generative framework is the ML solution. Finally, we evaluate our approach via simula(cid:173) tions of linear and nonlinear models on mixture of Gaussians and ICA problems. The experiments show the broad applicability and generality of our approach.", "bibtex": "@inproceedings{NIPS2000_6e79ed05,\n author = {Hochreiter, Sepp and Mozer, Michael C},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Beyond Maximum Likelihood and Density Estimation: A Sample-Based Criterion for Unsupervised Learning of Complex Models},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/6e79ed05baec2754e25b4eac73a332d2-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/6e79ed05baec2754e25b4eac73a332d2-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/6e79ed05baec2754e25b4eac73a332d2-Metadata.json", "review": "", "metareview": "", "pdf_size": 1376551, "gs_citation": 8, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=5104403255210945129&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 5, "aff": "Department of Computer Science, University of Colorado; Department of Computer Science, University of Colorado", "aff_domain": "cs.colorado.edu;cs.colorado.edu", "email": "cs.colorado.edu;cs.colorado.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "University of Colorado", "aff_unique_dep": "Department of Computer Science", "aff_unique_url": "https://www.colorado.edu", "aff_unique_abbr": "CU", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "2530fe92eb", "title": "Color Opponency Constitutes a Sparse Representation for the Chromatic Structure of Natural Scenes", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/0609154fa35b3194026346c9cac2a248-Abstract.html", "author": "Te-Won Lee; Thomas Wachtler; Terrence J. Sejnowski", "abstract": "The human visual system encodes the chromatic signals conveyed by the three types of retinal cone photoreceptors in an opponent fashion. This color opponency has been shown to constitute an efficient encoding by spectral decorrelation of the receptor signals. We analyze the spatial and chromatic structure of natural scenes by decomposing the spectral images into a set of linear basis functions such that they constitute a representation with minimal redun(cid:173) dancy. Independent component analysis finds the basis functions that transforms the spatiochromatic data such that the outputs (activations) are statistically as independent as possible, i.e. least redundant. The resulting basis functions show strong opponency along an achromatic direction (luminance edges), along a blue(cid:173) yellow direction, and along a red-blue direction. Furthermore, the resulting activations have very sparse distributions, suggesting that the use of color opponency in the human visual system achieves a highly efficient representation of colors. Our findings suggest that color opponency is a result of the properties of natural spectra and not solely a consequence of the overlapping cone spectral sensitiv(cid:173) ities.", "bibtex": "@inproceedings{NIPS2000_0609154f,\n author = {Lee, Te-Won and Wachtler, Thomas and Sejnowski, Terrence J},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Color Opponency Constitutes a Sparse Representation for the Chromatic Structure of Natural Scenes},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/0609154fa35b3194026346c9cac2a248-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/0609154fa35b3194026346c9cac2a248-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/0609154fa35b3194026346c9cac2a248-Metadata.json", "review": "", "metareview": "", "pdf_size": 1368067, "gs_citation": 9, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=15095560966862679236&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 10, "aff": "Institute for Neural Computation, University of California, San Diego + Computational Neurobiology Laboratory, The Salk Institute; Institute for Neural Computation, University of California, San Diego + Computational Neurobiology Laboratory, The Salk Institute; Institute for Neural Computation, University of California, San Diego + Computational Neurobiology Laboratory, The Salk Institute", "aff_domain": "salk.edu;salk.edu;salk.edu", "email": "salk.edu;salk.edu;salk.edu", "github": "", "project": "www.cnl.salk.edu/tewon", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0+1;0+1;0+1", "aff_unique_norm": "University of California, San Diego;Salk Institute", "aff_unique_dep": "Institute for Neural Computation;Computational Neurobiology Laboratory", "aff_unique_url": "https://www.ucsd.edu;https://www.salk.edu", "aff_unique_abbr": "UCSD;", "aff_campus_unique_index": "0;0;0", "aff_campus_unique": "San Diego;", "aff_country_unique_index": "0+0;0+0;0+0", "aff_country_unique": "United States" }, { "id": "45259a72db", "title": "Combining ICA and Top-Down Attention for Robust Speech Recognition", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f2d887e01a80e813d9080038decbbabb-Abstract.html", "author": "Un-Min Bae; Soo-Young Lee", "abstract": "We present an algorithm which compensates for the mismatches between characteristics of real-world problems and assumptions of independent component analysis algorithm. To provide additional information to the ICA network, we incorporate top-down selec(cid:173) tive attention. An MLP classifier is added to the separated signal channel and the error of the classifier is backpropagated to the ICA network. This backpropagation process results in estimation of expected ICA output signal for the top-down attention. Then, the unmixing matrix is retrained according to a new cost function representing the backpropagated error as well as independence. It modifies the density of recovered signals to the density appropriate for classification. For noisy speech signal recorded in real environ(cid:173) ments, the algorithm improved the recognition performance and showed robustness against parametric changes.", "bibtex": "@inproceedings{NIPS2000_f2d887e0,\n author = {Bae, Un-Min and Lee, Soo-Young},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Combining ICA and Top-Down Attention for Robust Speech Recognition},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f2d887e01a80e813d9080038decbbabb-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f2d887e01a80e813d9080038decbbabb-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f2d887e01a80e813d9080038decbbabb-Metadata.json", "review": "", "metareview": "", "pdf_size": 1221879, "gs_citation": 2, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11845327916579299176&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 5, "aff": "Department of Electrical Engineering and Computer Science and Brain Science Research Center, Korea Advanced Institute of Science and Technology; Department of Electrical Engineering and Computer Science and Brain Science Research Center, Korea Advanced Institute of Science and Technology", "aff_domain": "neuron.kaist.ac.kr;ee.kaist.ac.kr", "email": "neuron.kaist.ac.kr;ee.kaist.ac.kr", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Korea Advanced Institute of Science and Technology", "aff_unique_dep": "Department of Electrical Engineering and Computer Science", "aff_unique_url": "https://www.kaist.ac.kr", "aff_unique_abbr": "KAIST", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "South Korea" }, { "id": "d31d3b4201", "title": "Competition and Arbors in Ocular Dominance", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/c91591a8d461c2869b9f535ded3e213e-Abstract.html", "author": "Peter Dayan", "abstract": "Hebbian and competitive Hebbian algorithms are almost ubiquitous in modeling pattern formation in cortical development. We analyse in the(cid:173) oretical detail a particular model (adapted from Piepenbrock & Ober(cid:173) mayer, 1999) for the development of Id stripe-like patterns, which places competitive and interactive cortical influences, and free and restricted ini(cid:173) tial arborisation onto a common footing.", "bibtex": "@inproceedings{NIPS2000_c91591a8,\n author = {Dayan, Peter},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Competition and Arbors in Ocular Dominance},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/c91591a8d461c2869b9f535ded3e213e-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/c91591a8d461c2869b9f535ded3e213e-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/c91591a8d461c2869b9f535ded3e213e-Metadata.json", "review": "", "metareview": "", "pdf_size": 1459728, "gs_citation": 9, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=7147469645463438705&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 11, "aff": "Gatsby Computational Neuroscience Unit, UCL", "aff_domain": "gatsby.ucl.ac.uk", "email": "gatsby.ucl.ac.uk", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "University College London", "aff_unique_dep": "Gatsby Computational Neuroscience Unit", "aff_unique_url": "https://www.ucl.ac.uk", "aff_unique_abbr": "UCL", "aff_country_unique_index": "0", "aff_country_unique": "United Kingdom" }, { "id": "3033c99ad3", "title": "Computing with Finite and Infinite Networks", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/8562ae5e286544710b2e7ebe9858833b-Abstract.html", "author": "Ole Winther", "abstract": "Using statistical mechanics results, I calculate learning curves (average generalization error) for Gaussian processes (GPs) and Bayesian neural networks (NNs) used for regression. Applying the results to learning a teacher defined by a two-layer network, I can directly compare GP and Bayesian NN learning. I find that a GP in general requires CJ (d S )-training examples to learn input features of order s (d is the input dimension), whereas a NN can learn the task with order the number of adjustable weights training examples. Since a GP can be considered as an infinite NN, the results show that even in the Bayesian approach, it is important to limit the complexity of the learning machine. The theoretical findings are confirmed in simulations with analytical GP learning and a NN mean field algorithm.", "bibtex": "@inproceedings{NIPS2000_8562ae5e,\n author = {Winther, Ole},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Computing with Finite and Infinite Networks},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/8562ae5e286544710b2e7ebe9858833b-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/8562ae5e286544710b2e7ebe9858833b-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/8562ae5e286544710b2e7ebe9858833b-Metadata.json", "review": "", "metareview": "", "pdf_size": 1248121, "gs_citation": 9, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=9806670754300159937&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 15, "aff": "Theoretical Physics, Lund University", "aff_domain": "nimis.thep.lu.se", "email": "nimis.thep.lu.se", "github": "", "project": "http://www.thep.lu.se/tf2/staff/winther/", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "Lund University", "aff_unique_dep": "Theoretical Physics", "aff_unique_url": "https://www.lunduniversity.lu.se", "aff_unique_abbr": "LU", "aff_country_unique_index": "0", "aff_country_unique": "Sweden" }, { "id": "fef493fff5", "title": "Constrained Independent Component Analysis", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/8d55a249e6baa5c06772297520da2051-Abstract.html", "author": "Wei Lu; Jagath C. Rajapakse", "abstract": "The paper presents a novel technique of constrained independent component analysis (CICA) to introduce constraints into the clas(cid:173) sical ICA and solve the constrained optimization problem by using Lagrange multiplier methods. This paper shows that CICA can be used to order the resulted independent components in a specific manner and normalize the demixing matrix in the signal separation procedure. It can systematically eliminate the ICA's indeterminacy on permutation and dilation. The experiments demonstrate the use of CICA in ordering of independent components while providing normalized demixing processes. Keywords: Independent component analysis, constrained indepen(cid:173) dent component analysis, constrained optimization, Lagrange mul(cid:173) tiplier methods", "bibtex": "@inproceedings{NIPS2000_8d55a249,\n author = {Lu, Wei and Rajapakse, Jagath},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Constrained Independent Component Analysis},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/8d55a249e6baa5c06772297520da2051-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/8d55a249e6baa5c06772297520da2051-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/8d55a249e6baa5c06772297520da2051-Metadata.json", "review": "", "metareview": "", "pdf_size": 1301783, "gs_citation": 114, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=5317941020965592216&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 4, "aff": "School of Computer Engineering, Nanyang Technological University, Singapore 639798; School of Computer Engineering, Nanyang Technological University, Singapore 639798", "aff_domain": "ntu.edu.sg;ntu.edu.sg", "email": "ntu.edu.sg;ntu.edu.sg", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Nanyang Technological University", "aff_unique_dep": "School of Computer Engineering", "aff_unique_url": "https://www.ntu.edu.sg", "aff_unique_abbr": "NTU", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Singapore", "aff_country_unique_index": "0;0", "aff_country_unique": "Singapore" }, { "id": "fc5b92cdaf", "title": "Convergence of Large Margin Separable Linear Classification", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/13168e6a2e6c84b4b7de9390c0ef5ec5-Abstract.html", "author": "Tong Zhang", "abstract": "Large margin linear classification methods have been successfully ap(cid:173) plied to many applications. For a linearly separable problem, it is known that under appropriate assumptions, the expected misclassification error of the computed \"optimal hyperplane\" approaches zero at a rate propor(cid:173) tional to the inverse training sample size. This rate is usually charac(cid:173) terized by the margin and the maximum norm of the input data. In this paper, we argue that another quantity, namely the robustness of the in(cid:173) put data distribution, also plays an important role in characterizing the convergence behavior of expected misclassification error. Based on this concept of robustness, we show that for a large margin separable linear classification problem, the expected misclassification error may converge exponentially in the number of training sample size.", "bibtex": "@inproceedings{NIPS2000_13168e6a,\n author = {Zhang, Tong},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Convergence of Large Margin Separable Linear Classification},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/13168e6a2e6c84b4b7de9390c0ef5ec5-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/13168e6a2e6c84b4b7de9390c0ef5ec5-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/13168e6a2e6c84b4b7de9390c0ef5ec5-Metadata.json", "review": "", "metareview": "", "pdf_size": 1284470, "gs_citation": 19, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=9369153742651555910&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 12, "aff": "Mathematical Sciences Department, IBM TJ. Watson Research Center", "aff_domain": "watson.ibm.com", "email": "watson.ibm.com", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "IBM", "aff_unique_dep": "Mathematical Sciences Department", "aff_unique_url": "https://www.ibm.com/research/watson", "aff_unique_abbr": "IBM Watson", "aff_country_unique_index": "0", "aff_country_unique": "United States" }, { "id": "61c1dfa5a9", "title": "Data Clustering by Markovian Relaxation and the Information Bottleneck Method", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/e06f967fb0d355592be4e7674fa31d26-Abstract.html", "author": "Naftali Tishby; Noam Slonim", "abstract": "We introduce a new, non-parametric and principled, distance based clustering method. This method combines a pairwise based ap(cid:173) proach with a vector-quantization method which provide a mean(cid:173) ingful interpretation to the resulting clusters. The idea is based on turning the distance matrix into a Markov process and then examine the decay of mutual-information during the relaxation of this process. The clusters emerge as quasi-stable structures dur(cid:173) ing this relaxation, and then are extracted using the information bottleneck method. These clusters capture the information about the initial point of the relaxation in the most effective way. The method can cluster data with no geometric or other bias and makes no assumption about the underlying distribution.", "bibtex": "@inproceedings{NIPS2000_e06f967f,\n author = {Tishby, Naftali and Slonim, Noam},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Data Clustering by Markovian Relaxation and the Information Bottleneck Method},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/e06f967fb0d355592be4e7674fa31d26-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/e06f967fb0d355592be4e7674fa31d26-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/e06f967fb0d355592be4e7674fa31d26-Metadata.json", "review": "", "metareview": "", "pdf_size": 1392521, "gs_citation": 207, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=15515789393289102392&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 8, "aff": "School of Computer Science and Engineering and Center for Neural Computation*; School of Computer Science and Engineering and Center for Neural Computation*", "aff_domain": "cs.huji.ac.il;cs.huji.ac.il", "email": "cs.huji.ac.il;cs.huji.ac.il", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "School of Computer Science and Engineering", "aff_unique_dep": "Computer Science and Engineering", "aff_unique_url": "", "aff_unique_abbr": "", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "428ec57ddc", "title": "Decomposition of Reinforcement Learning for Admission Control of Self-Similar Call Arrival Processes", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/b432f34c5a997c8e7c806a895ecc5e25-Abstract.html", "author": "Jakob Carlstr\u00f6m", "abstract": "This paper presents predictive gain scheduling, a technique for simplify(cid:173) ing reinforcement learning problems by decomposition. Link admission control of self-similar call traffic is used to demonstrate the technique. The control problem is decomposed into on-line prediction of near-fu(cid:173) ture call arrival rates, and precomputation of policies for Poisson call ar(cid:173) rival processes. At decision time, the predictions are used to select among the policies. Simulations show that this technique results in sig(cid:173) nificantly faster learning without any performance loss, compared to a reinforcement learning controller that does not decompose the problem.", "bibtex": "@inproceedings{NIPS2000_b432f34c,\n author = {Carlstr\\\"{o}m, Jakob},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Decomposition of Reinforcement Learning for Admission Control of Self-Similar Call Arrival Processes},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/b432f34c5a997c8e7c806a895ecc5e25-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/b432f34c5a997c8e7c806a895ecc5e25-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/b432f34c5a997c8e7c806a895ecc5e25-Metadata.json", "review": "", "metareview": "", "pdf_size": 1435332, "gs_citation": 6, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=15220997177291139276&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 6, "aff": "Department of Electrical Engineering, Technion, Haifa 32000, Israel", "aff_domain": "ee.technion.ac.il", "email": "ee.technion.ac.il", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "Technion", "aff_unique_dep": "Department of Electrical Engineering", "aff_unique_url": "https://www.technion.ac.il", "aff_unique_abbr": "Technion", "aff_campus_unique_index": "0", "aff_campus_unique": "Haifa", "aff_country_unique_index": "0", "aff_country_unique": "Israel" }, { "id": "9b7df7941e", "title": "Dendritic Compartmentalization Could Underlie Competition and Attentional Biasing of Simultaneous Visual Stimuli", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/ff1418e8cc993fe8abcfe3ce2003e5c5-Abstract.html", "author": "Kevin A. Archie; Bartlett W. Mel", "abstract": "Neurons in area V4 have relatively large receptive fields (RFs), so multi(cid:173) ple visual features are simultaneously \"seen\" by these cells. Recordings from single V 4 neurons suggest that simultaneously presented stimuli compete to set the output firing rate, and that attention acts to isolate individual features by biasing the competition in favor of the attended object. We propose that both stimulus competition and attentional bias(cid:173) ing arise from the spatial segregation of afferent synapses onto different regions of the excitable dendritic tree of V 4 neurons. The pattern of feed(cid:173) forward, stimulus-driven inputs follows from a Hebbian rule: excitatory afferents with similar RFs tend to group together on the dendritic tree, avoiding randomly located inhibitory inputs with similar RFs. The same principle guides the formation of inputs that mediate attentional mod(cid:173) ulation. Using both biophysically detailed compartmental models and simplified models of computation in single neurons, we demonstrate that such an architecture could account for the response properties and atten(cid:173) tional modulation of V 4 neurons. Our results suggest an important role for nonlinear dendritic conductances in extrastriate cortical processing.", "bibtex": "@inproceedings{NIPS2000_ff1418e8,\n author = {Archie, Kevin and Mel, Bartlett},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Dendritic Compartmentalization Could Underlie Competition and Attentional Biasing of Simultaneous Visual Stimuli},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/ff1418e8cc993fe8abcfe3ce2003e5c5-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/ff1418e8cc993fe8abcfe3ce2003e5c5-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/ff1418e8cc993fe8abcfe3ce2003e5c5-Metadata.json", "review": "", "metareview": "", "pdf_size": 1375131, "gs_citation": 6, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=14617350081119471062&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 10, "aff": "Neuroscience Program, University of Southern California, Los Angeles, CA 90089-2520; Department of Biomedical Engineering, University of Southern California, Los Angeles, CA 90089-1451", "aff_domain": ";", "email": ";", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "University of Southern California", "aff_unique_dep": "Neuroscience Program", "aff_unique_url": "https://www.usc.edu", "aff_unique_abbr": "USC", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Los Angeles", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "4b875ecf92", "title": "Direct Classification with Indirect Data", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/8c8a58fa97c205ff222de3685497742c-Abstract.html", "author": "Timothy X. Brown", "abstract": "We classify an input space according to the outputs of a real-valued function. The function is not given, but rather examples of the function. We contribute a consistent classifier that avoids the un(cid:173) necessary complexity of estimating the function.", "bibtex": "@inproceedings{NIPS2000_8c8a58fa,\n author = {Brown, Timothy},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Direct Classification with Indirect Data},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/8c8a58fa97c205ff222de3685497742c-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/8c8a58fa97c205ff222de3685497742c-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/8c8a58fa97c205ff222de3685497742c-Metadata.json", "review": "", "metareview": "", "pdf_size": 1263753, "gs_citation": -1, "gs_cited_by_link": "", "gs_version_total": -1, "aff": "", "aff_domain": "", "email": "", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster" }, { "id": "2f44d3bf8e", "title": "Discovering Hidden Variables: A Structure-Based Approach", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/95e6834d0a3d99e9ea8811855ae9229d-Abstract.html", "author": "Gal Elidan; Noam Lotner; Nir Friedman; Daphne Koller", "abstract": "A serious problem in learning probabilistic models is the presence of hid(cid:173) den variables. These variables are not observed, yet interact with several of the observed variables. As such, they induce seemingly complex de(cid:173) pendencies among the latter. In recent years, much attention has been devoted to the development of algorithms for learning parameters, and in some cases structure, in the presence of hidden variables. In this pa(cid:173) per, we address the related problem of detecting hidden variables that interact with the observed variables. This problem is of interest both for improving our understanding of the domain and as a preliminary step that guides the learning procedure towards promising models. A very natural approach is to search for \"structural signatures\" of hidden variables - substructures in the learned network that tend to suggest the presence of a hidden variable. We make this basic idea concrete, and show how to integrate it with structure-search algorithms. We evaluate this method on several synthetic and real-life datasets, and show that it performs surpris(cid:173) ingly well.", "bibtex": "@inproceedings{NIPS2000_95e6834d,\n author = {Elidan, Gal and Lotner, Noam and Friedman, Nir and Koller, Daphne},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Discovering Hidden Variables: A Structure-Based Approach},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/95e6834d0a3d99e9ea8811855ae9229d-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/95e6834d0a3d99e9ea8811855ae9229d-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/95e6834d0a3d99e9ea8811855ae9229d-Metadata.json", "review": "", "metareview": "", "pdf_size": 1675268, "gs_citation": 171, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=1333752659920348223&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 21, "aff": "Hebrew University; Hebrew University; Hebrew University; Stanford University", "aff_domain": "cs.huji.ac.il;cs.huji.ac.il;cs.huji.ac.il;cs.stanford.edu", "email": "cs.huji.ac.il;cs.huji.ac.il;cs.huji.ac.il;cs.stanford.edu", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0;1", "aff_unique_norm": "Hebrew University of Jerusalem;Stanford University", "aff_unique_dep": ";", "aff_unique_url": "https://www.huji.ac.il;https://www.stanford.edu", "aff_unique_abbr": "HUJI;Stanford", "aff_campus_unique_index": "1", "aff_campus_unique": ";Stanford", "aff_country_unique_index": "0;0;0;1", "aff_country_unique": "Israel;United States" }, { "id": "82158a5daf", "title": "Divisive and Subtractive Mask Effects: Linking Psychophysics and Biophysics", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/faacbcd5bf1d018912c116bf2783e9a1-Abstract.html", "author": "Barbara Zenger; Christof Koch", "abstract": "We describe an analogy between psychophysically measured effects in contrast masking, and the behavior of a simple integrate-and(cid:173) fire neuron that receives time-modulated inhibition. In the psy(cid:173) chophysical experiments, we tested observers ability to discriminate contrasts of peripheral Gabor patches in the presence of collinear Gabor flankers. The data reveal a complex interaction pattern that we account for by assuming that flankers provide divisive inhibi(cid:173) tion to the target unit for low target contrasts, but provide sub(cid:173) tractive inhibition to the target unit for higher target contrasts. A similar switch from divisive to subtractive inhibition is observed in an integrate-and-fire unit that receives inhibition modulated in time such that the cell spends part of the time in a high-inhibition state and part of the time in a low-inhibition state. The simi(cid:173) larity between the effects suggests that one may cause the other. The biophysical model makes testable predictions for physiological single-cell recordings.", "bibtex": "@inproceedings{NIPS2000_faacbcd5,\n author = {Zenger, Barbara and Koch, Christof},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Divisive and Subtractive Mask Effects: Linking Psychophysics and Biophysics},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/faacbcd5bf1d018912c116bf2783e9a1-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/faacbcd5bf1d018912c116bf2783e9a1-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/faacbcd5bf1d018912c116bf2783e9a1-Metadata.json", "review": "", "metareview": "", "pdf_size": 1360252, "gs_citation": 4, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=13779126298806781899&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 5, "aff": "Division of Biology, Caltech 139-74, Pasadena, CA 91125; Computation and Neural Systems, Caltech 139-74, Pasadena, CA 91125", "aff_domain": "klab.caltech.edu;klab.caltech.edu", "email": "klab.caltech.edu;klab.caltech.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "California Institute of Technology", "aff_unique_dep": "Division of Biology", "aff_unique_url": "https://www.caltech.edu", "aff_unique_abbr": "Caltech", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Pasadena", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "4cde5c5532", "title": "Dopamine Bonuses", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/2f25f6e326adb93c5787175dda209ab6-Abstract.html", "author": "Sham Kakade; Peter Dayan", "abstract": "Substantial data support a temporal difference (TO) model of dopamine (OA) neuron activity in which the cells provide a global error signal for reinforcement learning. However, in certain cir(cid:173) cumstances, OA activity seems anomalous under the TO model, responding to non-rewarding stimuli. We address these anoma(cid:173) lies by suggesting that OA cells multiplex information about re(cid:173) ward bonuses, including Sutton's exploration bonuses and Ng et al's non-distorting shaping bonuses. We interpret this additional role for OA in terms of the unconditional attentional and psy(cid:173) chomotor effects of dopamine, having the computational role of guiding exploration.", "bibtex": "@inproceedings{NIPS2000_2f25f6e3,\n author = {Kakade, Sham and Dayan, Peter},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Dopamine Bonuses},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/2f25f6e326adb93c5787175dda209ab6-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/2f25f6e326adb93c5787175dda209ab6-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/2f25f6e326adb93c5787175dda209ab6-Metadata.json", "review": "", "metareview": "", "pdf_size": 1526238, "gs_citation": 28, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=2157382352857075298&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 15, "aff": ";", "aff_domain": ";", "email": ";", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster" }, { "id": "2937867360", "title": "Efficient Learning of Linear Perceptrons", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/39027dfad5138c9ca0c474d71db915c3-Abstract.html", "author": "Shai Ben-David; Hans-Ulrich Simon", "abstract": "We consider the existence of efficient algorithms for learning the class of half-spaces in ~n in the agnostic learning model (Le., mak(cid:173) ing no prior assumptions on the example-generating distribution). The resulting combinatorial problem - finding the best agreement half-space over an input sample - is NP hard to approximate to within some constant factor. We suggest a way to circumvent this theoretical bound by introducing a new measure of success for such algorithms. An algorithm is IL-margin successful if the agreement ratio of the half-space it outputs is as good as that of any half-space once training points that are inside the IL-margins of its separating hyper-plane are disregarded. We prove crisp computational com(cid:173) plexity results with respect to this success measure: On one hand, for every positive IL, there exist efficient (poly-time) IL-margin suc(cid:173) cessful learning algorithms. On the other hand, we prove that unless P=NP, there is no algorithm that runs in time polynomial in the sample size and in 1/ IL that is IL-margin successful for all IL> O.", "bibtex": "@inproceedings{NIPS2000_39027dfa,\n author = {Ben-David, Shai and Simon, Hans-Ulrich},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Efficient Learning of Linear Perceptrons},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/39027dfad5138c9ca0c474d71db915c3-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/39027dfad5138c9ca0c474d71db915c3-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/39027dfad5138c9ca0c474d71db915c3-Metadata.json", "review": "", "metareview": "", "pdf_size": 1324301, "gs_citation": 43, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=8769765503225933999&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 11, "aff": "Department of Computer Science, Technion, Haifa 32000, Israel; Fakultat fur Mathematik, Ruhr Universitat Bochum, D-44780 Bochum, Germany", "aff_domain": "cs.technion.ac.il;lmi.ruhr-uni-bochum.de", "email": "cs.technion.ac.il;lmi.ruhr-uni-bochum.de", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Technion;Ruhr Universitat Bochum", "aff_unique_dep": "Department of Computer Science;Fakultat fur Mathematik", "aff_unique_url": "https://www.technion.ac.il;https://www.ruhr-uni-bochum.de", "aff_unique_abbr": "Technion;", "aff_campus_unique_index": "0;1", "aff_campus_unique": "Haifa;Bochum", "aff_country_unique_index": "0;1", "aff_country_unique": "Israel;Germany" }, { "id": "03fca786b1", "title": "Emergence of Movement Sensitive Neurons' Properties by Learning a Sparse Code for Natural Moving Images", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/136f951362dab62e64eb8e841183c2a9-Abstract.html", "author": "Rafal Bogacz; Malcolm W. Brown; Christophe G. Giraud-Carrier", "abstract": "Olshausen & Field demonstrated that a learning algorithm that attempts to generate a sparse code for natural scenes develops a complete family of localised, oriented, bandpass receptive fields, similar to those of 'simple cells' in VI. This paper describes an algorithm which finds a sparse code for sequences of images that preserves information about the input. This algorithm when trained on natural video sequences develops bases representing the movement in particular directions with particular speeds, similar to the receptive fields of the movement-sensitive cells observed in cortical visual areas. Furthermore, to previous approaches to learning direction selectivity, the timing of neuronal activity encodes the phase of the movement, so the precise timing of spikes is crucially important to the information encoding.", "bibtex": "@inproceedings{NIPS2000_136f9513,\n author = {Bogacz, Rafal and Brown, Malcolm and Giraud-Carrier, Christophe},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Emergence of Movement Sensitive Neurons\\textquotesingle Properties by Learning a Sparse Code for Natural Moving Images},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/136f951362dab62e64eb8e841183c2a9-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/136f951362dab62e64eb8e841183c2a9-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/136f951362dab62e64eb8e841183c2a9-Metadata.json", "review": "", "metareview": "", "pdf_size": 732975, "gs_citation": 13, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=4886743794092685320&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 11, "aff": "Dept. of Computer Science, University of Bristol; Dept. of Anatomy, University of Bristol; Dept. of Computer Science, University of Bristol", "aff_domain": "bri.l'fol.ac.uk;bri.l'fol.ac.uk;c.l'.bri.l'.ac.uk", "email": "bri.l'fol.ac.uk;bri.l'fol.ac.uk;c.l'.bri.l'.ac.uk", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0", "aff_unique_norm": "University of Bristol", "aff_unique_dep": "Dept. of Computer Science", "aff_unique_url": "https://www.bristol.ac.uk", "aff_unique_abbr": "UoB", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United Kingdom" }, { "id": "c598bce25c", "title": "Ensemble Learning and Linear Response Theory for ICA", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/d1e946f4e67db4b362ad23818a6fb78a-Abstract.html", "author": "Pedro A. d. F. R. H\u00f8jen-S\u00f8rensen; Ole Winther; Lars Kai Hansen", "abstract": "We propose a general Bayesian framework for performing independent component analysis (leA) which relies on ensemble learning and lin(cid:173) ear response theory known from statistical physics. We apply it to both discrete and continuous sources. For the continuous source the underde(cid:173) termined (overcomplete) case is studied. The naive mean-field approach fails in this case whereas linear response theory-which gives an improved estimate of covariances-is very efficient. The examples given are for sources without temporal correlations. However, this derivation can eas(cid:173) ily be extended to treat temporal correlations. Finally, the framework offers a simple way of generating new leA algorithms without needing to define the prior distribution of the sources explicitly.", "bibtex": "@inproceedings{NIPS2000_d1e946f4,\n author = {H\\o jen-S\\o rensen, Pedro and Winther, Ole and Hansen, Lars},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Ensemble Learning and Linear Response Theory for ICA},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/d1e946f4e67db4b362ad23818a6fb78a-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/d1e946f4e67db4b362ad23818a6fb78a-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/d1e946f4e67db4b362ad23818a6fb78a-Metadata.json", "review": "", "metareview": "", "pdf_size": 1113389, "gs_citation": 5, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=16180999840616928265&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 16, "aff": "Department of Mathematical Modelling, Technical University of Denmark; Theoretical Physics, Lund University; Department of Mathematical Modelling, Technical University of Denmark", "aff_domain": "imrn.dtu.dk;nimis.thep.lu.se;imrn.dtu.dk", "email": "imrn.dtu.dk;nimis.thep.lu.se;imrn.dtu.dk", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;1;0", "aff_unique_norm": "Technical University of Denmark;Lund University", "aff_unique_dep": "Department of Mathematical Modelling;Theoretical Physics", "aff_unique_url": "https://www.teknologisk.dk;https://www.lunduniversity.lu.se", "aff_unique_abbr": "DTU;LU", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;1;0", "aff_country_unique": "Denmark;Sweden" }, { "id": "9b139d54a3", "title": "Error-correcting Codes on a Bethe-like Lattice", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/3fab5890d8113d0b5a4178201dc842ad-Abstract.html", "author": "Renato Vicente; David Saad; Yoshiyuki Kabashima", "abstract": "We analyze Gallager codes by employing a simple mean-field approxi(cid:173) mation that distorts the model geometry and preserves important interac(cid:173) tions between sites. The method naturally recovers the probability prop(cid:173) agation decoding algorithm as an extremization of a proper free-energy. We find a thermodynamic phase transition that coincides with informa(cid:173) tion theoretical upper-bounds and explain the practical code performance in terms of the free-energy landscape.", "bibtex": "@inproceedings{NIPS2000_3fab5890,\n author = {Vicente, Renato and Saad, David and Kabashima, Yoshiyuki},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Error-correcting Codes on a Bethe-like Lattice},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/3fab5890d8113d0b5a4178201dc842ad-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/3fab5890d8113d0b5a4178201dc842ad-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/3fab5890d8113d0b5a4178201dc842ad-Metadata.json", "review": "", "metareview": "", "pdf_size": 1302858, "gs_citation": 1, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=3010000339338364732&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 12, "aff": "The Neural Computing Research Group, Aston University, Birmingham, B4 7ET, United Kingdom; The Neural Computing Research Group, Aston University, Birmingham, B4 7ET, United Kingdom; Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, Yokohama 2268502, Japan", "aff_domain": "aston.ac.uk;aston.ac.uk;dis.titech.ac.jp", "email": "aston.ac.uk;aston.ac.uk;dis.titech.ac.jp", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;1", "aff_unique_norm": "Aston University;Tokyo Institute of Technology", "aff_unique_dep": "Neural Computing Research Group;Department of Computational Intelligence and Systems Science", "aff_unique_url": "https://www.aston.ac.uk;https://www.titech.ac.jp", "aff_unique_abbr": ";Titech", "aff_campus_unique_index": "0;0;1", "aff_campus_unique": "Birmingham;Yokohama", "aff_country_unique_index": "0;0;1", "aff_country_unique": "United Kingdom;Japan" }, { "id": "04a87fb83a", "title": "Exact Solutions to Time-Dependent MDPs", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/09b15d48a1514d8209b192a8b8f34e48-Abstract.html", "author": "Justin A. Boyan; Michael L. Littman", "abstract": "We describe an extension of the Markov decision process model in which a continuous time dimension is included in the state space. This allows for the representation and exact solution of a wide range of problems in which transitions or rewards vary over time. We examine problems based on route planning with public trans(cid:173) portation and telescope observation scheduling.", "bibtex": "@inproceedings{NIPS2000_09b15d48,\n author = {Boyan, Justin and Littman, Michael},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Exact Solutions to Time-Dependent MDPs},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/09b15d48a1514d8209b192a8b8f34e48-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/09b15d48a1514d8209b192a8b8f34e48-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/09b15d48a1514d8209b192a8b8f34e48-Metadata.json", "review": "", "metareview": "", "pdf_size": 1331412, "gs_citation": 173, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=1000094612831571101&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 11, "aff": "ITA Software; AT&T Labs-Research + Duke University", "aff_domain": "itasoftware.com;research.att.com", "email": "itasoftware.com;research.att.com", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1+2", "aff_unique_norm": "ITA Software;AT&T Labs;Duke University", "aff_unique_dep": ";Research;", "aff_unique_url": "https://www.itasoftware.com;https://www.att.com/labs/research;https://www.duke.edu", "aff_unique_abbr": ";AT&T Labs;Duke", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0+0", "aff_country_unique": "United States" }, { "id": "32684d783a", "title": "Explaining Away in Weight Space", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/eb1e78328c46506b46a4ac4a1e378b91-Abstract.html", "author": "Peter Dayan; Sham Kakade", "abstract": "Explaining away has mostly been considered in terms of inference of states in belief networks. We show how it can also arise in a Bayesian context in inference about the weights governing relationships such as those between stimuli and reinforcers in conditioning experiments such as bacA,'Ward blocking. We show how explaining away in weight space can be accounted for using an extension of a Kalman filter model; pro(cid:173) vide a new approximate way of looking at the Kalman gain matrix as a whitener for the correlation matrix of the observation process; suggest a network implementation of this whitener using an architecture due to Goodall; and show that the resulting model exhibits backward blocking.", "bibtex": "@inproceedings{NIPS2000_eb1e7832,\n author = {Dayan, Peter and Kakade, Sham},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Explaining Away in Weight Space},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/eb1e78328c46506b46a4ac4a1e378b91-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/eb1e78328c46506b46a4ac4a1e378b91-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/eb1e78328c46506b46a4ac4a1e378b91-Metadata.json", "review": "", "metareview": "", "pdf_size": 1392990, "gs_citation": 80, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=5768957856496600312&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 22, "aff": "Gatsby Computational Neuroscience Unit, UCL; Gatsby Computational Neuroscience Unit, UCL", "aff_domain": "gatsby.ucl.ac.uk;gatsby.ucl.ac.uk", "email": "gatsby.ucl.ac.uk;gatsby.ucl.ac.uk", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "University College London", "aff_unique_dep": "Gatsby Computational Neuroscience Unit", "aff_unique_url": "https://www.ucl.ac.uk", "aff_unique_abbr": "UCL", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "United Kingdom" }, { "id": "71d82e9d67", "title": "FaceSync: A Linear Operator for Measuring Synchronization of Video Facial Images and Audio Tracks", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/9f6992966d4c363ea0162a056cb45fe5-Abstract.html", "author": "Malcolm Slaney; Michele Covell", "abstract": "FaceSync is an optimal linear algorithm that finds the degree of syn(cid:173) chronization between the audio and image recordings of a human speaker. Using canonical correlation, it finds the best direction to com(cid:173) bine all the audio and image data, projecting them onto a single axis. FaceSync uses Pearson's correlation to measure the degree of synchro(cid:173) nization between the audio and image data. We derive the optimal linear transform to combine the audio and visual information and describe an implementation that avoids the numerical problems caused by comput(cid:173) ing the correlation matrices.", "bibtex": "@inproceedings{NIPS2000_9f699296,\n author = {Slaney, Malcolm and Covell, Michele},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {FaceSync: A Linear Operator for Measuring Synchronization of Video Facial Images and Audio Tracks},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/9f6992966d4c363ea0162a056cb45fe5-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/9f6992966d4c363ea0162a056cb45fe5-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/9f6992966d4c363ea0162a056cb45fe5-Metadata.json", "review": "", "metareview": "", "pdf_size": 1386586, "gs_citation": 235, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=4976952835299351478&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 19, "aff": "Interval Research + IBM Almaden Research; Interval Research + Yes Video", "aff_domain": "ieee.org;ieee.org", "email": "ieee.org;ieee.org", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0+1;0+2", "aff_unique_norm": "Interval Research Corporation;IBM;Yes Video", "aff_unique_dep": ";Research;", "aff_unique_url": "http://www.intervalresearch.com/;https://www.ibm.com/research;", "aff_unique_abbr": ";IBM;", "aff_campus_unique_index": "1;", "aff_campus_unique": ";Almaden", "aff_country_unique_index": "0+0;0", "aff_country_unique": "United States;" }, { "id": "11087db439", "title": "Factored Semi-Tied Covariance Matrices", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/fb8feff253bb6c834deb61ec76baa893-Abstract.html", "author": "Mark J. F. Gales", "abstract": "A new form of covariance modelling for Gaussian mixture models and hidden Markov models is presented. This is an extension to an efficient form of covariance modelling used in speech recognition, semi-tied co(cid:173) variance matrices. In the standard form of semi-tied covariance matrices the covariance matrix is decomposed into a highly shared decorrelating transform and a component-specific diagonal covariance matrix. The use of a factored decorrelating transform is presented in this paper. This fac(cid:173) toring effectively increases the number of possible transforms without in(cid:173) creasing the number of free parameters. Maximum likelihood estimation schemes for all the model parameters are presented including the compo(cid:173) nent/transform assignment, transform and component parameters. This new model form is evaluated on a large vocabulary speech recognition task. It is shown that using this factored form of covariance modelling reduces the word error rate.", "bibtex": "@inproceedings{NIPS2000_fb8feff2,\n author = {Gales, Mark},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Factored Semi-Tied Covariance Matrices},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/fb8feff253bb6c834deb61ec76baa893-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/fb8feff253bb6c834deb61ec76baa893-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/fb8feff253bb6c834deb61ec76baa893-Metadata.json", "review": "", "metareview": "", "pdf_size": 1271228, "gs_citation": 16, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=1350940041672829453&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 8, "aff": "Cambridge University Engineering Department", "aff_domain": "eng.cam.ac.uk", "email": "eng.cam.ac.uk", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "Cambridge University", "aff_unique_dep": "Engineering Department", "aff_unique_url": "https://www.cam.ac.uk", "aff_unique_abbr": "Cambridge", "aff_campus_unique_index": "0", "aff_campus_unique": "Cambridge", "aff_country_unique_index": "0", "aff_country_unique": "United Kingdom" }, { "id": "79e2312374", "title": "Fast Training of Support Vector Classifiers", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/6ae07dcb33ec3b7c814df797cbda0f87-Abstract.html", "author": "Fernando P\u00e9rez-Cruz; Pedro Luis Alarc\u00f3n-Diana; Angel Navia-V\u00e1zquez; Antonio Art\u00e9s-Rodr\u00edguez", "abstract": "In this communication we present a new algorithm for solving Support Vector Classifiers (SVC) with large training data sets. The new algorithm is based on an Iterative Re-Weighted Least Squares procedure which is used to optimize the SVc. Moreover, a novel sample selection strategy for the working set is presented, which randomly chooses the working set among the training samples that do not fulfill the stopping criteria. The validity of both proposals, the optimization procedure and sample selection strategy, is shown by means of computer experiments using well-known data sets.", "bibtex": "@inproceedings{NIPS2000_6ae07dcb,\n author = {P\\'{e}rez-Cruz, Fernando and Alarc\\'{o}n-Diana, Pedro and Navia-V\\'{a}zquez, Angel and Art\\'{e}s-Rodr\\'{\\i}guez, Antonio},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Fast Training of Support Vector Classifiers},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/6ae07dcb33ec3b7c814df797cbda0f87-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/6ae07dcb33ec3b7c814df797cbda0f87-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/6ae07dcb33ec3b7c814df797cbda0f87-Metadata.json", "review": "", "metareview": "", "pdf_size": 1344504, "gs_citation": 53, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=9058341695747111725&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 3, "aff": "Dpto. Teoria de la Seiial y Com., Escuela Politecnica, Universidad de Alcala; Dpto. Tecnologias de las comunicaciones, Escuela Politecnica Superior, Universidad Carlos ill de Madrid; Dpto. Tecnologias de las comunicaciones, Escuela Politecnica Superior, Universidad Carlos ill de Madrid; Dpto. Tecnologias de las comunicaciones, Escuela Politecnica Superior, Universidad Carlos ill de Madrid", "aff_domain": "tsc.uc3m.es; ; ;", "email": "tsc.uc3m.es; ; ;", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster", "aff_unique_index": "0;1;1;1", "aff_unique_norm": "Universidad de Alcala;Universidad Carlos III de Madrid", "aff_unique_dep": "Dpto. Teoria de la Seiial y Com.;Dpto. Tecnologias de las comunicaciones", "aff_unique_url": "https://www.uah.es;https://www.uc3m.es", "aff_unique_abbr": ";UC3M", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0;0;0", "aff_country_unique": "Spain" }, { "id": "92f4122d93", "title": "Feature Correspondence: A Markov Chain Monte Carlo Approach", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/d7657583058394c828ee150fada65345-Abstract.html", "author": "Frank Dellaert; Steven M. Seitz; Sebastian Thrun; Charles E. Thorpe", "abstract": "When trying to recover 3D structure from a set of images, the most difficult problem is establishing the correspondence between the measurements. Most existing approaches assume that features can be tracked across frames, whereas methods that exploit rigidity constraints to facilitate matching do so only under restricted cam(cid:173) era motion. In this paper we propose a Bayesian approach that avoids the brittleness associated with singling out one \"best\" cor(cid:173) respondence, and instead consider the distribution over all possible correspondences. We treat both a fully Bayesian approach that yields a posterior distribution, and a MAP approach that makes use of EM to maximize this posterior. We show how Markov chain Monte Carlo methods can be used to implement these techniques in practice, and present experimental results on real data.", "bibtex": "@inproceedings{NIPS2000_d7657583,\n author = {Dellaert, Frank and Seitz, Steven and Thrun, Sebastian and Thorpe, Charles},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Feature Correspondence: A Markov Chain Monte Carlo Approach},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/d7657583058394c828ee150fada65345-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/d7657583058394c828ee150fada65345-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/d7657583058394c828ee150fada65345-Metadata.json", "review": "", "metareview": "", "pdf_size": 1308143, "gs_citation": 41, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=16421263584409949388&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 22, "aff": ";;;", "aff_domain": ";;;", "email": ";;;", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster" }, { "id": "e901bbc00e", "title": "Feature Selection for SVMs", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/8c3039bd5842dca3d944faab91447818-Abstract.html", "author": "Jason Weston; Sayan Mukherjee; Olivier Chapelle; Massimiliano Pontil; Tomaso Poggio; Vladimir Vapnik", "abstract": "We introduce a method of feature selection for Support Vector Machines. The method is based upon finding those features which minimize bounds on the leave-one-out error. This search can be efficiently performed via gradient descent. The resulting algorithms are shown to be superior to some standard feature selection algorithms on both toy data and real-life problems of face recognition, pedestrian detection and analyzing DNA micro array data.", "bibtex": "@inproceedings{NIPS2000_8c3039bd,\n author = {Weston, Jason and Mukherjee, Sayan and Chapelle, Olivier and Pontil, Massimiliano and Poggio, Tomaso and Vapnik, Vladimir},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Feature Selection for SVMs},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/8c3039bd5842dca3d944faab91447818-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/8c3039bd5842dca3d944faab91447818-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/8c3039bd5842dca3d944faab91447818-Metadata.json", "review": "", "metareview": "", "pdf_size": 1306116, "gs_citation": 1597, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=18297955194656076851&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 30, "aff": "Barnhill Biolnformatics.com, Savannah, Georgia, USA; CBCL MIT, Cambridge, Massachusetts, USA; AT&T Research Laboratories, Red Bank, USA; CBCL MIT, Cambridge, Massachusetts, USA; CBCL MIT, Cambridge, Massachusetts, USA; Royal Holloway, University of London, Egham, Surrey, UK", "aff_domain": ";;;;;", "email": ";;;;;", "github": "", "project": "", "author_num": 6, "track": "main", "status": "Poster", "aff_unique_index": "0;1;2;1;1;3", "aff_unique_norm": "Barnhill Bioinformatics;Massachusetts Institute of Technology;AT&T Research Laboratories;University of London", "aff_unique_dep": ";CBCL;;", "aff_unique_url": ";https://web.mit.edu/;https://www.att.com/research;https://www.royalholloway.ac.uk", "aff_unique_abbr": ";MIT;AT&T;RHUL", "aff_campus_unique_index": "0;1;2;1;1;3", "aff_campus_unique": "Savannah;Cambridge;Red Bank;Egham", "aff_country_unique_index": "0;0;0;0;0;1", "aff_country_unique": "United States;United Kingdom" }, { "id": "bc701d1c71", "title": "Finding the Key to a Synapse", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f542eae1949358e25d8bfeefe5b199f1-Abstract.html", "author": "Thomas Natschl\u00e4ger; Wolfgang Maass", "abstract": "Experimental data have shown that synapses are heterogeneous: different synapses respond with different sequences of amplitudes of postsynaptic responses to the same spike train. Neither the role of synaptic dynamics itself nor the role of the heterogeneity of synaptic dynamics for com(cid:173) putations in neural circuits is well understood. We present in this article methods that make it feasible to compute for a given synapse with known synaptic parameters the spike train that is optimally fitted to the synapse, for example in the sense that it produces the largest sum of postsynap(cid:173) tic responses. To our surprise we find that most of these optimally fitted spike trains match common firing patterns of specific types of neurons that are discussed in the literature.", "bibtex": "@inproceedings{NIPS2000_f542eae1,\n author = {Natschl\\\"{a}ger, Thomas and Maass, Wolfgang},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Finding the Key to a Synapse},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f542eae1949358e25d8bfeefe5b199f1-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f542eae1949358e25d8bfeefe5b199f1-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f542eae1949358e25d8bfeefe5b199f1-Metadata.json", "review": "", "metareview": "", "pdf_size": 1335454, "gs_citation": 14, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=106091761695203016&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 14, "aff": "Institute for Theoretical Computer Science, Technische Universitat Graz, Austria; Institute for Theoretical Computer Science, Technische Universitat Graz, Austria", "aff_domain": "igi.tu-graz.ac.at;igi.tu-graz.ac.at", "email": "igi.tu-graz.ac.at;igi.tu-graz.ac.at", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Technische Universitat Graz", "aff_unique_dep": "Institute for Theoretical Computer Science", "aff_unique_url": "https://www.tugraz.at", "aff_unique_abbr": "", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "Austria" }, { "id": "cfa2269e4a", "title": "Foundations for a Circuit Complexity Theory of Sensory Processing", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/ab7314887865c4265e896c6e209d1cd6-Abstract.html", "author": "Robert A. Legenstein; Wolfgang Maass", "abstract": "We introduce total wire length as salient complexity measure for an anal(cid:173) ysis of the circuit complexity of sensory processing in biological neural systems and neuromorphic engineering. This new complexity measure is applied to a set of basic computational problems that apparently need to be solved by circuits for translation- and scale-invariant sensory process(cid:173) ing. We exhibit new circuit design strategies for these new benchmark functions that can be implemented within realistic complexity bounds, in particular with linear or almost linear total wire length.", "bibtex": "@inproceedings{NIPS2000_ab731488,\n author = {Legenstein, Robert and Maass, Wolfgang},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Foundations for a Circuit Complexity Theory of Sensory Processing},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/ab7314887865c4265e896c6e209d1cd6-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/ab7314887865c4265e896c6e209d1cd6-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/ab7314887865c4265e896c6e209d1cd6-Metadata.json", "review": "", "metareview": "", "pdf_size": 1530082, "gs_citation": 20, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=3470527883187684841&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 13, "aff": "Institute for Theoretical Computer Science, Technische Universitat Graz, Austria; Institute for Theoretical Computer Science, Technische Universitat Graz, Austria", "aff_domain": "igi.tu-graz.ac.at;igi.tu-graz.ac.at", "email": "igi.tu-graz.ac.at;igi.tu-graz.ac.at", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Technische Universitat Graz", "aff_unique_dep": "Institute for Theoretical Computer Science", "aff_unique_url": "https://www.tugraz.at", "aff_unique_abbr": "", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "Austria" }, { "id": "2cc01ea8b3", "title": "Four-legged Walking Gait Control Using a Neuromorphic Chip Interfaced to a Support Vector Learning Algorithm", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/2647c1dba23bc0e0f9cdf75339e120d2-Abstract.html", "author": "Susanne Still; Bernhard Sch\u00f6lkopf; Klaus Hepp; Rodney J. Douglas", "abstract": "To control the walking gaits of a four-legged robot we present a novel neuromorphic VLSI chip that coordinates the relative phasing of the robot's legs similar to how spinal Central Pattern Generators are believed to control vertebrate locomotion [3]. The chip controls the leg move(cid:173) ments by driving motors with time varying voltages which are the out(cid:173) puts of a small network of coupled oscillators. The characteristics of the chip's output voltages depend on a set of input parameters. The rela(cid:173) tionship between input parameters and output voltages can be computed analytically for an idealized system. In practice, however, this ideal re(cid:173) lationship is only approximately true due to transistor mismatch and off(cid:173) sets. Fine tuning of the chip's input parameters is done automatically by the robotic system, using an unsupervised Support Vector (SV) learning algorithm introduced recently [7]. The learning requires only that the description of the desired output is given. The machine learns from (un(cid:173) labeled) examples how to set the parameters to the chip in order to obtain a desired motor behavior.", "bibtex": "@inproceedings{NIPS2000_2647c1db,\n author = {Still, Susanne and Sch\\\"{o}lkopf, Bernhard and Hepp, Klaus and Douglas, Rodney},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Four-legged Walking Gait Control Using a Neuromorphic Chip Interfaced to a Support Vector Learning Algorithm},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/2647c1dba23bc0e0f9cdf75339e120d2-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/2647c1dba23bc0e0f9cdf75339e120d2-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/2647c1dba23bc0e0f9cdf75339e120d2-Metadata.json", "review": "", "metareview": "", "pdf_size": 1412374, "gs_citation": 22, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11703433291400701611&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 9, "aff": "NEC Research Institute 4 Independence Way, Princeton NJ 08540, USA; Institute of Theoretical Physics ETH Zurich, Switzerland; Microsoft Research Institute 1 Guildhall Street, Cambridge, UK; Institute of Neuroinformatics ETHIUNI Zurich, Switzerland", "aff_domain": "research.nj.nec.com; ;scientist.com; ", "email": "research.nj.nec.com; ;scientist.com; ", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster", "aff_unique_index": "0;1;2;1", "aff_unique_norm": "NEC Research Institute;ETH Zurich;Microsoft", "aff_unique_dep": ";Institute of Theoretical Physics;Microsoft Research", "aff_unique_url": "https://www.neci.nec.com;https://www.ethz.ch;https://www.microsoft.com/en-us/research", "aff_unique_abbr": "NECRI;ETHZ;MSR", "aff_campus_unique_index": "0;2;3", "aff_campus_unique": "Princeton;;Cambridge;Zurich", "aff_country_unique_index": "0;1;2;1", "aff_country_unique": "United States;Switzerland;United Kingdom" }, { "id": "97ea34e847", "title": "From Margin to Sparsity", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/d305281faf947ca7acade9ad5c8c818c-Abstract.html", "author": "Thore Graepel; Ralf Herbrich; Robert C. Williamson", "abstract": "We present an improvement of Novikoff's perceptron convergence theorem. Reinterpreting this mistake bound as a margin dependent sparsity guarantee allows us to give a PAC-style generalisation er(cid:173) ror bound for the classifier learned by the perceptron learning algo(cid:173) rithm. The bound value crucially depends on the margin a support vector machine would achieve on the same data set using the same kernel. Ironically, the bound yields better guarantees than are cur(cid:173) rently available for the support vector solution itself.", "bibtex": "@inproceedings{NIPS2000_d305281f,\n author = {Graepel, Thore and Herbrich, Ralf and Williamson, Robert C},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {From Margin to Sparsity},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/d305281faf947ca7acade9ad5c8c818c-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/d305281faf947ca7acade9ad5c8c818c-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/d305281faf947ca7acade9ad5c8c818c-Metadata.json", "review": "", "metareview": "", "pdf_size": 1228700, "gs_citation": 63, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=5062623781784856477&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 11, "aff": "Computer Science Department, Technical University of Berlin, Berlin, Germany; Computer Science Department, Technical University of Berlin, Berlin, Germany; Department of Engineering, Australian National University, Canberra, Australia", "aff_domain": "cs.tu-berlin.de;cs.tu-berlin.de;anu.edu.au", "email": "cs.tu-berlin.de;cs.tu-berlin.de;anu.edu.au", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;1", "aff_unique_norm": "Technical University of Berlin;Australian National University", "aff_unique_dep": "Computer Science Department;Department of Engineering", "aff_unique_url": "https://www.tu-berlin.de;https://www.anu.edu.au", "aff_unique_abbr": "TU Berlin;ANU", "aff_campus_unique_index": "0;0;1", "aff_campus_unique": "Berlin;Canberra", "aff_country_unique_index": "0;0;1", "aff_country_unique": "Germany;Australia" }, { "id": "a3a581a6df", "title": "From Mixtures of Mixtures to Adaptive Transform Coding", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/4888241374e8c62ddd9b4c3cfd091f96-Abstract.html", "author": "Cynthia Archer; Todd K. Leen", "abstract": "We establish a principled framework for adaptive transform cod(cid:173) ing. Transform coders are often constructed by concatenating an ad hoc choice of transform with suboptimal bit allocation and quan(cid:173) tizer design. Instead, we start from a probabilistic latent variable model in the form of a mixture of constrained Gaussian mixtures. From this model we derive a transform coding algorithm, which is a constrained version of the generalized Lloyd algorithm for vector quantizer design. A byproduct of our derivation is the introduc(cid:173) tion of a new transform basis, which unlike other transforms (PCA, DCT, etc.) is explicitly optimized for coding. Image compression experiments show adaptive transform coders designed with our al(cid:173) gorithm improve compressed image signal-to-noise ratio up to 3 dB compared to global transform coding and 0.5 to 2 dB compared to other adaptive transform coders.", "bibtex": "@inproceedings{NIPS2000_48882413,\n author = {Archer, Cynthia and Leen, Todd},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {From Mixtures of Mixtures to Adaptive Transform Coding},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/4888241374e8c62ddd9b4c3cfd091f96-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/4888241374e8c62ddd9b4c3cfd091f96-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/4888241374e8c62ddd9b4c3cfd091f96-Metadata.json", "review": "", "metareview": "", "pdf_size": 1309624, "gs_citation": 9, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=12921323825460586431&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 9, "aff": ";", "aff_domain": ";", "email": ";", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster" }, { "id": "31af4dd9ef", "title": "Gaussianization", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/3c947bc2f7ff007b86a9428b74654de5-Abstract.html", "author": "Scott Saobing Chen; Ramesh A. Gopinath", "abstract": "High dimensional data modeling is difficult mainly because the so-called \"curse of dimensionality\". We propose a technique called \"Gaussianiza(cid:173) tion\" for high dimensional density estimation, which alleviates the curse of dimensionality by exploiting the independence structures in the data. Gaussianization is motivated from recent developments in the statistics literature: projection pursuit, independent component analysis and Gaus(cid:173) sian mixture models with semi-tied covariances. We propose an iter(cid:173) ative Gaussianization procedure which converges weakly: at each it(cid:173) eration, the data is first transformed to the least dependent coordinates and then each coordinate is marginally Gaussianized by univariate tech(cid:173) niques. Gaussianization offers density estimation sharper than traditional kernel methods and radial basis function methods. Gaussianization can be viewed as efficient solution of nonlinear independent component anal(cid:173) ysis and high dimensional projection pursuit.", "bibtex": "@inproceedings{NIPS2000_3c947bc2,\n author = {Chen, Scott and Gopinath, Ramesh},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Gaussianization},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/3c947bc2f7ff007b86a9428b74654de5-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/3c947bc2f7ff007b86a9428b74654de5-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/3c947bc2f7ff007b86a9428b74654de5-Metadata.json", "review": "", "metareview": "", "pdf_size": 1315787, "gs_citation": 201, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=12797393617749420818&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 7, "aff": "Renaissance Technologies, East Setauket, NY 11733; IBM TJ. Watson Research Center, Yorktown Heights, NY 10598", "aff_domain": "rentec.com;us.ibm.com", "email": "rentec.com;us.ibm.com", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Renaissance Technologies;IBM", "aff_unique_dep": ";IBM TJ. Watson Research Center", "aff_unique_url": "https://www.renaissancetechnologies.com;https://www.ibm.com/research/watson", "aff_unique_abbr": "RenTech;IBM Watson", "aff_campus_unique_index": "0;1", "aff_campus_unique": "East Setauket;Yorktown Heights", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "e3aa85e88b", "title": "Generalizable Singular Value Decomposition for Ill-posed Datasets", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/b4568df26077653eeadf29596708c94b-Abstract.html", "author": "Ulrik Kjems; Lars Kai Hansen; Stephen C. Strother", "abstract": "We demonstrate that statistical analysis of ill-posed data sets is subject to a bias, which can be observed when projecting indepen(cid:173) dent test set examples onto a basis defined by the training exam(cid:173) ples. Because the training examples in an ill-posed data set do not fully span the signal space the observed training set variances in each basis vector will be too high compared to the average vari(cid:173) ance of the test set projections onto the same basis vectors. On basis of this understanding we introduce the Generalizable Singu(cid:173) lar Value Decomposition (GenSVD) as a means to reduce this bias by re-estimation of the singular values obtained in a conventional Singular Value Decomposition, allowing for a generalization perfor(cid:173) mance increase of a subsequent statistical model. We demonstrate that the algorithm succesfully corrects bias in a data set from a functional PET activation study of the human brain.", "bibtex": "@inproceedings{NIPS2000_b4568df2,\n author = {Kjems, Ulrik and Hansen, Lars and Strother, Stephen},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Generalizable Singular Value Decomposition for Ill-posed Datasets},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/b4568df26077653eeadf29596708c94b-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/b4568df26077653eeadf29596708c94b-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/b4568df26077653eeadf29596708c94b-Metadata.json", "review": "", "metareview": "", "pdf_size": 1193923, "gs_citation": 22, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=13200818592034717051&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 7, "aff": "Department of Mathematical Modelling, Technical University of Denmark; Department of Mathematical Modelling, Technical University of Denmark; PET Imaging Service, VA medical center", "aff_domain": "imm.dtu.dk;imm.dtu.dk;pet.med.va.gov", "email": "imm.dtu.dk;imm.dtu.dk;pet.med.va.gov", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;1", "aff_unique_norm": "Technical University of Denmark;VA Medical Center", "aff_unique_dep": "Department of Mathematical Modelling;PET Imaging Service", "aff_unique_url": "https://www.teknologisk.dk;https://www.va.gov", "aff_unique_abbr": "DTU;", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0;1", "aff_country_unique": "Denmark;United States" }, { "id": "4c97278a45", "title": "Generalized Belief Propagation", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/61b1fb3f59e28c67f3925f3c79be81a1-Abstract.html", "author": "Jonathan S. Yedidia; William T. Freeman; Yair Weiss", "abstract": "Belief propagation (BP) was only supposed to work for tree-like networks but works surprisingly well in many applications involving networks with loops, including turbo codes. However, there has been little understanding of the algorithm or the nature of the solutions it finds for general graphs. We show that BP can only converge to a stationary point of an approximate free energy, known as the Bethe free energy in statis(cid:173) tical physics. This result characterizes BP fixed-points and makes connections with variational approaches to approximate inference. More importantly, our analysis lets us build on the progress made in statistical physics since Bethe's approximation was introduced in 1935. Kikuchi and others have shown how to construct more ac(cid:173) curate free energy approximations, of which Bethe's approximation is the simplest. Exploiting the insights from our analysis, we de(cid:173) rive generalized belief propagation (GBP) versions ofthese Kikuchi approximations. These new message passing algorithms can be significantly more accurate than ordinary BP, at an adjustable in(cid:173) crease in complexity. We illustrate such a new GBP algorithm on a grid Markov network and show that it gives much more accurate marginal probabilities than those found using ordinary BP.", "bibtex": "@inproceedings{NIPS2000_61b1fb3f,\n author = {Yedidia, Jonathan S and Freeman, William and Weiss, Yair},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Generalized Belief Propagation},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/61b1fb3f59e28c67f3925f3c79be81a1-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/61b1fb3f59e28c67f3925f3c79be81a1-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/61b1fb3f59e28c67f3925f3c79be81a1-Metadata.json", "review": "", "metareview": "", "pdf_size": 1446641, "gs_citation": 1543, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=2246695255130134179&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 14, "aff": "MERL; MERL; Computer Science Division, UC Berkeley", "aff_domain": "merl.com;merl.com;cs.berkeley.edu", "email": "merl.com;merl.com;cs.berkeley.edu", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;1", "aff_unique_norm": "Mitsubishi Electric Research Laboratories;University of California, Berkeley", "aff_unique_dep": ";Computer Science Division", "aff_unique_url": "https://www.merl.com;https://www.berkeley.edu", "aff_unique_abbr": "MERL;UC Berkeley", "aff_campus_unique_index": "1", "aff_campus_unique": ";Berkeley", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "1415c97adb", "title": "Hierarchical Memory-Based Reinforcement Learning", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/85f007f8c50dd25f5a45fca73cad64bd-Abstract.html", "author": "Natalia Hernandez-Gardiol; Sridhar Mahadevan", "abstract": "Sridhar Mahadevan", "bibtex": "@inproceedings{NIPS2000_85f007f8,\n author = {Hernandez-Gardiol, Natalia and Mahadevan, Sridhar},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Hierarchical Memory-Based Reinforcement Learning},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/85f007f8c50dd25f5a45fca73cad64bd-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/85f007f8c50dd25f5a45fca73cad64bd-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/85f007f8c50dd25f5a45fca73cad64bd-Metadata.json", "review": "", "metareview": "", "pdf_size": 1369324, "gs_citation": 119, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=8783646282479662734&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 0, "aff": "Artificial Intelligence Lab, Massachusetts Institute of Technology; Department of Computer Science, Michigan State University", "aff_domain": "ai.mit.edu;cse.msu.edu", "email": "ai.mit.edu;cse.msu.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Massachusetts Institute of Technology;Michigan State University", "aff_unique_dep": "Artificial Intelligence Lab;Department of Computer Science", "aff_unique_url": "https://www.mit.edu;https://www.msu.edu", "aff_unique_abbr": "MIT;MSU", "aff_campus_unique_index": "0", "aff_campus_unique": "Cambridge;", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "5b7bd09360", "title": "High-temperature Expansions for Learning Models of Nonnegative Data", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/139f0874f2ded2e41b0393c4ac5644f7-Abstract.html", "author": "Oliver B. Downs", "abstract": "Recent work has exploited boundedness of data in the unsupervised learning of new types of generative model. For nonnegative data it was recently shown that the maximum-entropy generative model is a Non(cid:173) negative Boltzmann Distribution not a Gaussian distribution, when the model is constrained to match the first and second order statistics of the data. Learning for practical sized problems is made difficult by the need to compute expectations under the model distribution. The computa(cid:173) tional cost of Markov chain Monte Carlo methods and low fidelity of naive mean field techniques has led to increasing interest in advanced mean field theories and variational methods. Here I present a second(cid:173) order mean-field approximation for the Nonnegative Boltzmann Machine model, obtained using a \"high-temperature\" expansion. The theory is tested on learning a bimodal 2-dimensional model, a high-dimensional translationally invariant distribution, and a generative model for hand(cid:173) written digits.", "bibtex": "@inproceedings{NIPS2000_139f0874,\n author = {Downs, Oliver},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {High-temperature Expansions for Learning Models of Nonnegative Data},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/139f0874f2ded2e41b0393c4ac5644f7-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/139f0874f2ded2e41b0393c4ac5644f7-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/139f0874f2ded2e41b0393c4ac5644f7-Metadata.json", "review": "", "metareview": "", "pdf_size": 1059288, "gs_citation": 6, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=12445617785856187625&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 9, "aff": "Dept. of Mathematics, Princeton University", "aff_domain": "princeton.edu", "email": "princeton.edu", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "Princeton University", "aff_unique_dep": "Department of Mathematics", "aff_unique_url": "https://www.princeton.edu", "aff_unique_abbr": "Princeton", "aff_campus_unique_index": "0", "aff_campus_unique": "Princeton", "aff_country_unique_index": "0", "aff_country_unique": "United States" }, { "id": "a6e7eccc6f", "title": "Higher-Order Statistical Properties Arising from the Non-Stationarity of Natural Signals", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/5103c3584b063c431bd1268e9b5e76fb-Abstract.html", "author": "Lucas C. Parra; Clay Spence; Paul Sajda", "abstract": "We present evidence that several higher-order statistical proper(cid:173) ties of natural images and signals can be explained by a stochastic model which simply varies scale of an otherwise stationary Gaus(cid:173) sian process. We discuss two interesting consequences. The first is that a variety of natural signals can be related through a com(cid:173) mon model of spherically invariant random processes, which have the attractive property that the joint densities can be constructed from the one dimensional marginal. The second is that in some cas(cid:173) es the non-stationarity assumption and only second order methods can be explicitly exploited to find a linear basis that is equivalent to independent components obtained with higher-order methods. This is demonstrated on spectro-temporal components of speech.", "bibtex": "@inproceedings{NIPS2000_5103c358,\n author = {Parra, Lucas and Spence, Clay and Sajda, Paul},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Higher-Order Statistical Properties Arising from the Non-Stationarity of Natural Signals},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/5103c3584b063c431bd1268e9b5e76fb-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/5103c3584b063c431bd1268e9b5e76fb-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/5103c3584b063c431bd1268e9b5e76fb-Metadata.json", "review": "", "metareview": "", "pdf_size": 1347820, "gs_citation": 49, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=14611989401862700713&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 9, "aff": "Adaptive Signal and Image Processing, Sarnoff Corporation; Adaptive Signal and Image Processing, Sarnoff Corporation; Department of biomedical Engineering, Columbia University", "aff_domain": "sarnofJ.com;sarnofJ.com;columbia.edu", "email": "sarnofJ.com;sarnofJ.com;columbia.edu", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;1", "aff_unique_norm": "Sarnoff Corporation;Columbia University", "aff_unique_dep": "Adaptive Signal and Image Processing;Department of Biomedical Engineering", "aff_unique_url": "https://www.sarnoff.com;https://www.columbia.edu", "aff_unique_abbr": ";Columbia", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "dab74e363c", "title": "Hippocampally-Dependent Consolidation in a Hierarchical Model of Neocortex", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/57c0531e13f40b91b3b0f1a30b529a1d-Abstract.html", "author": "Szabolcs K\u00e1li; Peter Dayan", "abstract": "In memory consolidation, declarative memories which initially require the hippocampus for their recall, ultimately become independent of it. Consolidation has been the focus of numerous experimental and qualita(cid:173) tive modeling studies, but only little quantitative exploration. We present a consolidation model in which hierarchical connections in the cortex, that initially instantiate purely semantic information acquired through probabilistic unsupervised learning, come to instantiate episodic infor(cid:173) mation as well. The hippocampus is responsible for helping complete partial input patterns before consolidation is complete, while also train(cid:173) ing the cortex to perform appropriate completion by itself.", "bibtex": "@inproceedings{NIPS2000_57c0531e,\n author = {K\\'{a}li, Szabolcs and Dayan, Peter},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Hippocampally-Dependent Consolidation in a Hierarchical Model of Neocortex},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/57c0531e13f40b91b3b0f1a30b529a1d-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/57c0531e13f40b91b3b0f1a30b529a1d-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/57c0531e13f40b91b3b0f1a30b529a1d-Metadata.json", "review": "", "metareview": "", "pdf_size": 414141, "gs_citation": 15, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=15613928625349186156&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 12, "aff": "Gatsby Computational Neuroscience Unit, University College London; Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology", "aff_domain": "gatsby.ucl.ac.uk; ", "email": "gatsby.ucl.ac.uk; ", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "University College London;Massachusetts Institute of Technology", "aff_unique_dep": "Gatsby Computational Neuroscience Unit;Department of Brain and Cognitive Sciences", "aff_unique_url": "https://www.ucl.ac.uk;https://web.mit.edu", "aff_unique_abbr": "UCL;MIT", "aff_campus_unique_index": "0;1", "aff_campus_unique": "London;Cambridge", "aff_country_unique_index": "0;1", "aff_country_unique": "United Kingdom;United States" }, { "id": "4d168a9da8", "title": "Homeostasis in a Silicon Integrate and Fire Neuron", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/414e773d5b7e5c06d564f594bf6384d0-Abstract.html", "author": "Shih-Chii Liu; Bradley A. Minch", "abstract": "In this work, we explore homeostasis in a silicon integrate-and-fire neu(cid:173) ron. The neuron adapts its firing rate over long time periods on the order of seconds or minutes so that it returns to its spontaneous firing rate after a lasting perturbation. Homeostasis is implemented via two schemes. One scheme looks at the presynaptic activity and adapts the synaptic weight depending on the presynaptic spiking rate. The second scheme adapts the synaptic \"threshold\" depending on the neuron's activity. The threshold is lowered if the neuron's activity decreases over a long time and is increased for prolonged increase in postsynaptic activity. Both these mechanisms for adaptation use floating-gate technology. The re(cid:173) sults shown here are measured from a chip fabricated in a 2-J.lm CMOS process.", "bibtex": "@inproceedings{NIPS2000_414e773d,\n author = {Liu, Shih-Chii and Minch, Bradley},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Homeostasis in a Silicon Integrate and Fire Neuron},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/414e773d5b7e5c06d564f594bf6384d0-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/414e773d5b7e5c06d564f594bf6384d0-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/414e773d5b7e5c06d564f594bf6384d0-Metadata.json", "review": "", "metareview": "", "pdf_size": 1058884, "gs_citation": 19, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11082791761430951451&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 8, "aff": "Institute for Neuroinformatics, ETH/UNIZ; School of Electrical and Computer Engineering, Cornell University", "aff_domain": "ini.phys.ethz.ch;ee.comell.edu", "email": "ini.phys.ethz.ch;ee.comell.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "ETH Zurich;Cornell University", "aff_unique_dep": "Institute for Neuroinformatics;School of Electrical and Computer Engineering", "aff_unique_url": "https://www.ethz.ch;https://www.cornell.edu", "aff_unique_abbr": "ETH;Cornell", "aff_campus_unique_index": "1", "aff_campus_unique": ";Ithaca", "aff_country_unique_index": "0;1", "aff_country_unique": "Switzerland;United States" }, { "id": "ea48c9f5ad", "title": "Improved Output Coding for Classification Using Continuous Relaxation", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/ecd62de20ea67e1c2d933d311b08178a-Abstract.html", "author": "Koby Crammer; Yoram Singer", "abstract": "Output coding is a general method for solving multiclass problems by reducing them to multiple binary classification problems. Previous re(cid:173) search on output coding has employed, almost solely, predefined discrete codes. We describe an algorithm that improves the performance of output codes by relaxing them to continuous codes. The relaxation procedure is cast as an optimization problem and is reminiscent of the quadratic program for support vector machines. We describe experiments with the proposed algorithm, comparing it to standard discrete output codes. The experimental results indicate that continuous relaxations of output codes often improve the generalization performance, especially for short codes.", "bibtex": "@inproceedings{NIPS2000_ecd62de2,\n author = {Crammer, Koby and Singer, Yoram},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Improved Output Coding for Classification Using Continuous Relaxation},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/ecd62de20ea67e1c2d933d311b08178a-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/ecd62de20ea67e1c2d933d311b08178a-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/ecd62de20ea67e1c2d933d311b08178a-Metadata.json", "review": "", "metareview": "", "pdf_size": 1364221, "gs_citation": 40, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=14626311726147061903&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 6, "aff": "School of Computer Science & Engineering, The Hebrew University, Jerusalem 91904, Israel; School of Computer Science & Engineering, The Hebrew University, Jerusalem 91904, Israel", "aff_domain": "cs.huji.ac.il;cs.huji.ac.il", "email": "cs.huji.ac.il;cs.huji.ac.il", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Hebrew University", "aff_unique_dep": "School of Computer Science & Engineering", "aff_unique_url": "http://www.huji.ac.il", "aff_unique_abbr": "HUJI", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Jerusalem", "aff_country_unique_index": "0;0", "aff_country_unique": "Israel" }, { "id": "a264bd3490", "title": "Incorporating Second-Order Functional Knowledge for Better Option Pricing", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/44968aece94f667e4095002d140b5896-Abstract.html", "author": "Charles Dugas; Yoshua Bengio; Fran\u00e7ois B\u00e9lisle; Claude Nadeau; Ren\u00e9 Garcia", "abstract": "Incorporating prior knowledge of a particular task into the architecture of a learning algorithm can greatly improve generalization performance. We study here a case where we know that the function to be learned is non-decreasing in two of its arguments and convex in one of them. For this purpose we propose a class of functions similar to multi-layer neural networks but (1) that has those properties, (2) is a universal approximator of continuous functions with these and other properties. We apply this new class of functions to the task of modeling the price of call options. Experiments show improvements on regressing the price of call options using the new types of function classes that incorporate the a priori con(cid:173) straints.", "bibtex": "@inproceedings{NIPS2000_44968aec,\n author = {Dugas, Charles and Bengio, Yoshua and B\\'{e}lisle, Fran\\c{c}ois and Nadeau, Claude and Garcia, Ren\\'{e}},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Incorporating Second-Order Functional Knowledge for Better Option Pricing},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/44968aece94f667e4095002d140b5896-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/44968aece94f667e4095002d140b5896-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/44968aece94f667e4095002d140b5896-Metadata.json", "review": "", "metareview": "", "pdf_size": 1285227, "gs_citation": 650, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11823176145601877272&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 13, "aff": "CIRANO, Montreal, Qc, Canada H3A 2A5; CIRANO, Montreal, Qc, Canada H3A 2A5; CIRANO, Montreal, Qc, Canada H3A 2A5; CIRANO, Montreal, Qc, Canada H3A 2A5 + Health Canada; CIRANO, Montreal, Qc, Canada H3A 2A5", "aff_domain": "iro.umontreal.ca;iro.umontreal.ca;iro.umontreal.ca;iro.umontreal.ca;cirano.qc.ca", "email": "iro.umontreal.ca;iro.umontreal.ca;iro.umontreal.ca;iro.umontreal.ca;cirano.qc.ca", "github": "", "project": "", "author_num": 5, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0;0+1;0", "aff_unique_norm": "CIRANO;Health Canada", "aff_unique_dep": ";", "aff_unique_url": ";https://www.canada.ca/en/health-canada.html", "aff_unique_abbr": ";HC", "aff_campus_unique_index": "0;0;0;0;0", "aff_campus_unique": "Montreal;", "aff_country_unique_index": "0;0;0;0+0;0", "aff_country_unique": "Canada" }, { "id": "7a2793179d", "title": "Incremental and Decremental Support Vector Machine Learning", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/155fa09596c7e18e50b58eb7e0c6ccb4-Abstract.html", "author": "Gert Cauwenberghs; Tomaso Poggio", "abstract": "An on-line recursive algorithm for training support vector machines, one vector at a time, is presented. Adiabatic increments retain the Kuhn(cid:173) Tucker conditions on all previously seen training data, in a number of steps each computed analytically. The incremental procedure is re(cid:173) versible, and decremental \"unlearning\" offers an efficient method to ex(cid:173) actly evaluate leave-one-out generalization performance. Interpretation of decremental unlearning in feature space sheds light on the relationship between generalization and geometry of the data.", "bibtex": "@inproceedings{NIPS2000_155fa095,\n author = {Cauwenberghs, Gert and Poggio, Tomaso},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Incremental and Decremental Support Vector Machine Learning},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/155fa09596c7e18e50b58eb7e0c6ccb4-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/155fa09596c7e18e50b58eb7e0c6ccb4-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/155fa09596c7e18e50b58eb7e0c6ccb4-Metadata.json", "review": "", "metareview": "", "pdf_size": 1090754, "gs_citation": 1886, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=17789278207283625101&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 18, "aff": "CLSP, ECE Dept., Johns Hopkins University, Baltimore, MD 21218; CBCL, BCS Dept., Massachusetts Institute of Technology, Cambridge, MA 02142", "aff_domain": "jhu.edu;ai.mit.edu", "email": "jhu.edu;ai.mit.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Johns Hopkins University;Massachusetts Institute of Technology", "aff_unique_dep": "Department of Electrical and Computer Engineering;BCS Dept.", "aff_unique_url": "https://www.jhu.edu;https://www.mit.edu", "aff_unique_abbr": "JHU;MIT", "aff_campus_unique_index": "0;1", "aff_campus_unique": "Baltimore;Cambridge", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "7c700c4270", "title": "Interactive Parts Model: An Application to Recognition of On-line Cursive Script", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/d54e99a6c03704e95e6965532dec148b-Abstract.html", "author": "Predrag Neskovic; Philip C. Davis; Leon N. Cooper", "abstract": "In this work, we introduce an Interactive Parts (IP) model as an alternative to Hidden Markov Models (HMMs). We tested both models on a database of on-line cursive script. We show that im(cid:173) plementations of HMMs and the IP model, in which all letters are assumed to have the same average width, give comparable results. However , in contrast to HMMs, the IP model can handle duration modeling without an increase in computational complexity.", "bibtex": "@inproceedings{NIPS2000_d54e99a6,\n author = {Neskovic, Predrag and Davis, Philip and Cooper, Leon},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Interactive Parts Model: An Application to Recognition of On-line Cursive Script},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/d54e99a6c03704e95e6965532dec148b-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/d54e99a6c03704e95e6965532dec148b-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/d54e99a6c03704e95e6965532dec148b-Metadata.json", "review": "", "metareview": "", "pdf_size": 1271422, "gs_citation": 12, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=8341643937565790628&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 9, "aff": ";;", "aff_domain": ";;", "email": ";;", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster" }, { "id": "06d4c6db41", "title": "Keeping Flexible Active Contours on Track using Metropolis Updates", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/dfce06801e1a85d6d06f1fdd4475dacd-Abstract.html", "author": "Trausti T. Kristjansson; Brendan J. Frey", "abstract": "Condensation, a form of likelihood-weighted particle filtering, has been successfully used to infer the shapes of highly constrained \"active\" con(cid:173) tours in video sequences. However, when the contours are highly flexible (e.g. for tracking fingers of a hand), a computationally burdensome num(cid:173) ber of particles is needed to successfully approximate the contour distri(cid:173) bution. We show how the Metropolis algorithm can be used to update a particle set representing a distribution over contours at each frame in a video sequence. We compare this method to condensation using a video sequence that requires highly flexible contours, and show that the new algorithm performs dramatically better that the condensation algorithm. We discuss the incorporation of this method into the \"active contour\" framework where a shape-subspace is used constrain shape variation.", "bibtex": "@inproceedings{NIPS2000_dfce0680,\n author = {Kristjansson, Trausti and Frey, Brendan J},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Keeping Flexible Active Contours on Track using Metropolis Updates},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/dfce06801e1a85d6d06f1fdd4475dacd-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/dfce06801e1a85d6d06f1fdd4475dacd-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/dfce06801e1a85d6d06f1fdd4475dacd-Metadata.json", "review": "", "metareview": "", "pdf_size": 1194371, "gs_citation": 2, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=9750077112500635925&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 7, "aff": "University of Waterloo; University of Waterloo", "aff_domain": "uwaterloo.ca;uwaterloo.ca", "email": "uwaterloo.ca;uwaterloo.ca", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "University of Waterloo", "aff_unique_dep": "", "aff_unique_url": "https://uwaterloo.ca", "aff_unique_abbr": "UW", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "Canada" }, { "id": "6c00e56b39", "title": "Kernel Expansions with Unlabeled Examples", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/5bce843dd76db8c939d5323dd3e54ec9-Abstract.html", "author": "Martin Szummer; Tommi Jaakkola", "abstract": "Modern classification applications necessitate supplementing the few available labeled examples with unlabeled examples to improve classi(cid:173) fication performance. We present a new tractable algorithm for exploit(cid:173) ing unlabeled examples in discriminative classification. This is achieved essentially by expanding the input vectors into longer feature vectors via both labeled and unlabeled examples. The resulting classification method can be interpreted as a discriminative kernel density estimate and is read(cid:173) ily trained via the EM algorithm, which in this case is both discriminative and achieves the optimal solution. We provide, in addition, a purely dis(cid:173) criminative formulation of the estimation problem by appealing to the maximum entropy framework. We demonstrate that the proposed ap(cid:173) proach requires very few labeled examples for high classification accu(cid:173) racy.", "bibtex": "@inproceedings{NIPS2000_5bce843d,\n author = {Szummer, Martin and Jaakkola, Tommi},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Kernel Expansions with Unlabeled Examples},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/5bce843dd76db8c939d5323dd3e54ec9-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/5bce843dd76db8c939d5323dd3e54ec9-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/5bce843dd76db8c939d5323dd3e54ec9-Metadata.json", "review": "", "metareview": "", "pdf_size": 1357912, "gs_citation": 52, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=17274163010547381757&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 14, "aff": "MIT AI Lab & CBCL; MIT AI Lab", "aff_domain": "ai.mit.edu;ai.mit.edu", "email": "ai.mit.edu;ai.mit.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Massachusetts Institute of Technology", "aff_unique_dep": "Artificial Intelligence Laboratory & Center for Biological and Computational Learning", "aff_unique_url": "http://www.ai.mit.edu", "aff_unique_abbr": "MIT AI Lab", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Cambridge", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "6cd95dead2", "title": "Kernel-Based Reinforcement Learning in Average-Cost Problems: An Application to Optimal Portfolio Choice", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/cd63a3eec3319fd9c84c942a08316e00-Abstract.html", "author": "Dirk Ormoneit; Peter W. Glynn", "abstract": "Many approaches to reinforcement learning combine neural net(cid:173) works or other parametric function approximators with a form of temporal-difference learning to estimate the value function of a Markov Decision Process. A significant disadvantage of those pro(cid:173) cedures is that the resulting learning algorithms are frequently un(cid:173) stable. In this work, we present a new, kernel-based approach to reinforcement learning which overcomes this difficulty and provably converges to a unique solution. By contrast to existing algorithms, our method can also be shown to be consistent in the sense that its costs converge to the optimal costs asymptotically. Our focus is on learning in an average-cost framework and on a practical ap(cid:173) plication to the optimal portfolio choice problem.", "bibtex": "@inproceedings{NIPS2000_cd63a3ee,\n author = {Ormoneit, Dirk and Glynn, Peter W},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Kernel-Based Reinforcement Learning in Average-Cost Problems: An Application to Optimal Portfolio Choice},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/cd63a3eec3319fd9c84c942a08316e00-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/cd63a3eec3319fd9c84c942a08316e00-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/cd63a3eec3319fd9c84c942a08316e00-Metadata.json", "review": "", "metareview": "", "pdf_size": 1355001, "gs_citation": 18, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=18255217211005141249&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 11, "aff": "Department of Computer Science, Stanford University; EESOR, Stanford University", "aff_domain": "cs.stanford.edu; ", "email": "cs.stanford.edu; ", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Stanford University", "aff_unique_dep": "Department of Computer Science", "aff_unique_url": "https://www.stanford.edu", "aff_unique_abbr": "Stanford", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Stanford", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "5d5ce585f0", "title": "Large Scale Bayes Point Machines", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/333222170ab9edca4785c39f55221fe7-Abstract.html", "author": "Ralf Herbrich; Thore Graepel", "abstract": "also known as the Bayes point -", "bibtex": "@inproceedings{NIPS2000_33322217,\n author = {Herbrich, Ralf and Graepel, Thore},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Large Scale Bayes Point Machines},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/333222170ab9edca4785c39f55221fe7-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/333222170ab9edca4785c39f55221fe7-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/333222170ab9edca4785c39f55221fe7-Metadata.json", "review": "", "metareview": "", "pdf_size": 1335703, "gs_citation": 22, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=2909682390654872127&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 8, "aff": "Statistics Research Group Computer Science Department Technical University of Berlin; Statistics Research Group Computer Science Department Technical University of Berlin", "aff_domain": "cs.tu-berlin.de;cs.tu-berlin.de", "email": "cs.tu-berlin.de;cs.tu-berlin.de", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Technical University of Berlin", "aff_unique_dep": "Computer Science Department", "aff_unique_url": "https://www.tu-berlin.de", "aff_unique_abbr": "TU Berlin", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "Germany" }, { "id": "39f47f19c0", "title": "Learning Continuous Distributions: Simulations With Field Theoretic Priors", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f39ae9ff3a81f499230c4126e01f421b-Abstract.html", "author": "Ilya Nemenman; William Bialek", "abstract": "Learning of a smooth but nonparametric probability density can be reg(cid:173) ularized using methods of Quantum Field Theory. We implement a field theoretic prior numerically, test its efficacy, and show that the free pa(cid:173) rameter of the theory (,smoothness scale') can be determined self con(cid:173) sistently by the data; this forms an infinite dimensional generalization of the MDL principle. Finally, we study the implications of one's choice of the prior and the parameterization and conclude that the smoothness scale determination makes density estimation very weakly sensitive to the choice of the prior, and that even wrong choices can be advantageous for small data sets.", "bibtex": "@inproceedings{NIPS2000_f39ae9ff,\n author = {Nemenman, Ilya and Bialek, William},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Learning Continuous Distributions: Simulations With Field Theoretic Priors},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f39ae9ff3a81f499230c4126e01f421b-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f39ae9ff3a81f499230c4126e01f421b-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f39ae9ff3a81f499230c4126e01f421b-Metadata.json", "review": "", "metareview": "", "pdf_size": 1366323, "gs_citation": 4, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=4744769113964841881&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 12, "aff": "Department of Physics, Princeton University, Princeton, New Jersey 08544 + NEC Research Institute, 4 Independence Way, Princeton, New Jersey 08540; NEC Research Institute, 4 Independence Way, Princeton, New Jersey 08540", "aff_domain": "research.nj.nec.com;research.nj.nec.com", "email": "research.nj.nec.com;research.nj.nec.com", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0+1;1", "aff_unique_norm": "Princeton University;NEC Research Institute", "aff_unique_dep": "Department of Physics;", "aff_unique_url": "https://www.princeton.edu;https://www.nec.com/research/", "aff_unique_abbr": "Princeton;NEC RI", "aff_campus_unique_index": "0", "aff_campus_unique": "Princeton;", "aff_country_unique_index": "0+0;0", "aff_country_unique": "United States" }, { "id": "80c6ae65d6", "title": "Learning Curves for Gaussian Processes Regression: A Framework for Good Approximations", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/ed519dacc89b2bead3f453b0b05a4a8b-Abstract.html", "author": "D\u00f6rthe Malzahn; Manfred Opper", "abstract": "Based on a statistical mechanics approach, we develop a method for approximately computing average case learning curves for Gaus(cid:173) sian process regression models. The approximation works well in the large sample size limit and for arbitrary dimensionality of the input space. We explain how the approximation can be systemati(cid:173) cally improved and argue that similar techniques can be applied to general likelihood models.", "bibtex": "@inproceedings{NIPS2000_ed519dac,\n author = {Malzahn, D\\\"{o}rthe and Opper, Manfred},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Learning Curves for Gaussian Processes Regression: A Framework for Good Approximations},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/ed519dacc89b2bead3f453b0b05a4a8b-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/ed519dacc89b2bead3f453b0b05a4a8b-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/ed519dacc89b2bead3f453b0b05a4a8b-Metadata.json", "review": "", "metareview": "", "pdf_size": 1194592, "gs_citation": 22, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=7266237990169686905&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 6, "aff": "Neural Computing Research Group, School of Engineering and Applied Science, Aston University, Birmingham B4 7ET, United Kingdom; Neural Computing Research Group, School of Engineering and Applied Science, Aston University, Birmingham B4 7ET, United Kingdom", "aff_domain": "aston.ac.uk;aston.ac.uk", "email": "aston.ac.uk;aston.ac.uk", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Aston University", "aff_unique_dep": "School of Engineering and Applied Science", "aff_unique_url": "https://www.aston.ac.uk", "aff_unique_abbr": "Aston", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Birmingham", "aff_country_unique_index": "0;0", "aff_country_unique": "United Kingdom" }, { "id": "3ac314b6e9", "title": "Learning Joint Statistical Models for Audio-Visual Fusion and Segregation", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/11f524c3fbfeeca4aa916edcb6b6392e-Abstract.html", "author": "John W. Fisher III; Trevor Darrell; William T. Freeman; Paul A. Viola", "abstract": "People can understand complex auditory and visual information, often using one to disambiguate the other. Automated analysis, even at a low(cid:173) level, faces severe challenges, including the lack of accurate statistical models for the signals, and their high-dimensionality and varied sam(cid:173) pling rates. Previous approaches [6] assumed simple parametric models for the joint distribution which, while tractable, cannot capture the com(cid:173) plex signal relationships. We learn the joint distribution of the visual and auditory signals using a non-parametric approach. First, we project the data into a maximally informative, low-dimensional subspace, suitable for density estimation. We then model the complicated stochastic rela(cid:173) tionships between the signals using a nonparametric density estimator. These learned densities allow processing across signal modalities. We demonstrate, on synthetic and real signals, localization in video of the face that is speaking in audio, and, conversely, audio enhancement of a particular speaker selected from the video.", "bibtex": "@inproceedings{NIPS2000_11f524c3,\n author = {Fisher III, John W and Darrell, Trevor and Freeman, William and Viola, Paul},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Learning Joint Statistical Models for Audio-Visual Fusion and Segregation},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/11f524c3fbfeeca4aa916edcb6b6392e-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/11f524c3fbfeeca4aa916edcb6b6392e-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/11f524c3fbfeeca4aa916edcb6b6392e-Metadata.json", "review": "", "metareview": "", "pdf_size": 1321105, "gs_citation": 271, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=13688422048138991796&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 11, "aff": "Massachusetts Institute of Technology; Mitsubishi Electric Research Laboratory; Massachusetts Institute of Technology; Massachusetts Institute of Technology", "aff_domain": "ai.mit.edu;merl.com;ai.mit.edu;ai.mit.edu", "email": "ai.mit.edu;merl.com;ai.mit.edu;ai.mit.edu", "github": "", "project": "http://www.ai.mit.edulpeople/fisher", "author_num": 4, "track": "main", "status": "Poster", "aff_unique_index": "0;1;0;0", "aff_unique_norm": "Massachusetts Institute of Technology;Mitsubishi Electric Research Laboratory", "aff_unique_dep": ";", "aff_unique_url": "https://web.mit.edu;https://www.merl.com", "aff_unique_abbr": "MIT;MERL", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0;0;0", "aff_country_unique": "United States" }, { "id": "0a750a5b9b", "title": "Learning Segmentation by Random Walks", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/069654d5ce089c13f642d19f09a3d1c0-Abstract.html", "author": "Marina Meila; Jianbo Shi", "abstract": "We present a new view of image segmentation by pairwise simi(cid:173) larities. We interpret the similarities as edge flows in a Markov random walk and study the eigenvalues and eigenvectors of the walk's transition matrix. This interpretation shows that spectral methods for clustering and segmentation have a probabilistic foun(cid:173) dation. In particular, we prove that the Normalized Cut method arises naturally from our framework. Finally, the framework pro(cid:173) vides a principled method for learning the similarity function as a combination of features.", "bibtex": "@inproceedings{NIPS2000_069654d5,\n author = {Meila, Marina and Shi, Jianbo},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Learning Segmentation by Random Walks},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/069654d5ce089c13f642d19f09a3d1c0-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/069654d5ce089c13f642d19f09a3d1c0-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/069654d5ce089c13f642d19f09a3d1c0-Metadata.json", "review": "", "metareview": "", "pdf_size": 1357080, "gs_citation": 649, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=16699120300369347706&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 7, "aff": "University of Washington; Carnegie Mellon University", "aff_domain": "stat.washington.edu;cs.cmu.edu", "email": "stat.washington.edu;cs.cmu.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "University of Washington;Carnegie Mellon University", "aff_unique_dep": ";", "aff_unique_url": "https://www.washington.edu;https://www.cmu.edu", "aff_unique_abbr": "UW;CMU", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "a19a4068d1", "title": "Learning Sparse Image Codes using a Wavelet Pyramid Architecture", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/dc5d637ed5e62c36ecb73b654b05ba2a-Abstract.html", "author": "Bruno A. Olshausen; Phil Sallee; Michael S. Lewicki", "abstract": "We show how a wavelet basis may be adapted to best represent natural images in terms of sparse coefficients. The wavelet basis, which may be either complete or overcomplete, is specified by a small number of spatial functions which are repeated across space and combined in a recursive fashion so as to be self-similar across scale. These functions are adapted to minimize the estimated code length under a model that assumes images are composed of a linear superposition of sparse, independent components. When adapted to natural images, the wavelet bases take on different orientations and they evenly tile the orientation domain, in stark contrast to the standard, non-oriented wavelet bases used in image compression. When the basis set is allowed to be overcomplete, it also yields higher coding efficiency than standard wavelet bases.", "bibtex": "@inproceedings{NIPS2000_dc5d637e,\n author = {Olshausen, Bruno and Sallee, Phil and Lewicki, Michael},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Learning Sparse Image Codes using a Wavelet Pyramid Architecture},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/dc5d637ed5e62c36ecb73b654b05ba2a-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/dc5d637ed5e62c36ecb73b654b05ba2a-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/dc5d637ed5e62c36ecb73b654b05ba2a-Metadata.json", "review": "", "metareview": "", "pdf_size": 1120199, "gs_citation": 113, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=6866047111978481044&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 12, "aff": "Department of Psychology and Center for Neuroscience, UC Davis; Department of Computer Science, UC Davis; Department of Computer Science and Center for the Neural Basis of Cognition, Carnegie Mellon University", "aff_domain": "uedavis.edu;es.uedavis.edu;enbe.emu.edu", "email": "uedavis.edu;es.uedavis.edu;enbe.emu.edu", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;1", "aff_unique_norm": "University of California, Davis;Carnegie Mellon University", "aff_unique_dep": "Department of Psychology and Center for Neuroscience;Department of Computer Science", "aff_unique_url": "https://www.ucdavis.edu;https://www.cmu.edu", "aff_unique_abbr": "UC Davis;CMU", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Davis;", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "0d520ae6b2", "title": "Learning Switching Linear Models of Human Motion", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/ca460332316d6da84b08b9bcf39b687b-Abstract.html", "author": "Vladimir Pavlovic; James M. Rehg; John MacCormick", "abstract": "The human figure exhibits complex and rich dynamic behavior that is both nonlinear and time-varying. Effective models of human dynamics can be learned from motion capture data using switching linear dynamic system (SLDS) models. We present results for human motion synthe(cid:173) sis, classification, and visual tracking using learned SLDS models. Since exact inference in SLDS is intractable, we present three approximate in(cid:173) ference algorithms and compare their performance. In particular, a new variational inference algorithm is obtained by casting the SLDS model as a Dynamic Bayesian Network. Classification experiments show the superiority of SLDS over conventional HMM's for our problem domain.", "bibtex": "@inproceedings{NIPS2000_ca460332,\n author = {Pavlovic, Vladimir and Rehg, James M and MacCormick, John},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Learning Switching Linear Models of Human Motion},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/ca460332316d6da84b08b9bcf39b687b-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/ca460332316d6da84b08b9bcf39b687b-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/ca460332316d6da84b08b9bcf39b687b-Metadata.json", "review": "", "metareview": "", "pdf_size": 1394175, "gs_citation": 482, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=8354031446932011051&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 26, "aff": "Compaq -Cambridge Research Lab; Compaq -Cambridge Research Lab; Compaq -System Research Center", "aff_domain": "compaq.com;compaq.com;compaq.com", "email": "compaq.com;compaq.com;compaq.com", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0", "aff_unique_norm": "Compaq", "aff_unique_dep": "Research Lab", "aff_unique_url": "https://www.compaq.com", "aff_unique_abbr": "", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Cambridge;", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "82b66e0d6a", "title": "Learning Winner-take-all Competition Between Groups of Neurons in Lateral Inhibitory Networks", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/aa2a77371374094fe9e0bc1de3f94ed9-Abstract.html", "author": "Xiaohui Xie; Richard H. R. Hahnloser; H. Sebastian Seung", "abstract": "It has long been known that lateral inhibition in neural networks can lead to a winner-take-all competition, so that only a single neuron is active at a steady state. Here we show how to organize lateral inhibition so that groups of neurons compete to be active. Given a collection of poten(cid:173) tially overlapping groups, the inhibitory connectivity is set by a formula that can be interpreted as arising from a simple learning rule. Our analy(cid:173) sis demonstrates that such inhibition generally results in winner-take-all competition between the given groups, with the exception of some de(cid:173) generate cases. In a broader context, the network serves as a particular illustration of the general distinction between permitted and forbidden sets, which was introduced recently. From this viewpoint, the computa(cid:173) tional function of our network is to store and retrieve memories as per(cid:173) mitted sets of coactive neurons.", "bibtex": "@inproceedings{NIPS2000_aa2a7737,\n author = {Xie, Xiaohui and Hahnloser, Richard and Seung, H. Sebastian},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Learning Winner-take-all Competition Between Groups of Neurons in Lateral Inhibitory Networks},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/aa2a77371374094fe9e0bc1de3f94ed9-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/aa2a77371374094fe9e0bc1de3f94ed9-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/aa2a77371374094fe9e0bc1de3f94ed9-Metadata.json", "review": "", "metareview": "", "pdf_size": 1306951, "gs_citation": 27, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11780145986300290894&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 10, "aff": "E25-21O, MIT, Cambridge, MA 02139; E25-21O, MIT, Cambridge, MA 02139; E25-21O, MIT, Cambridge, MA 02139", "aff_domain": "mit.edu;mit.edu;mit.edu", "email": "mit.edu;mit.edu;mit.edu", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0", "aff_unique_norm": "Massachusetts Institute of Technology", "aff_unique_dep": "", "aff_unique_url": "https://web.mit.edu", "aff_unique_abbr": "MIT", "aff_campus_unique_index": "0;0;0", "aff_campus_unique": "Cambridge", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "46e21cd4c0", "title": "Learning and Tracking Cyclic Human Motion", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/ad4cc1fb9b068faecfb70914acc63395-Abstract.html", "author": "Dirk Ormoneit; Hedvig Sidenbladh; Michael J. Black; Trevor Hastie", "abstract": "We present methods for learning and tracking human motion in video. We estimate a statistical model of typical activities from a large set of 3D periodic human motion data by segmenting these data automatically into \"cycles\". Then the mean and the princi(cid:173) pal components of the cycles are computed using a new algorithm that accounts for missing information and enforces smooth tran(cid:173) sitions between cycles. The learned temporal model provides a prior probability distribution over human motions that can be used in a Bayesian framework for tracking human subjects in complex monocular video sequences and recovering their 3D motion.", "bibtex": "@inproceedings{NIPS2000_ad4cc1fb,\n author = {Ormoneit, Dirk and Sidenbladh, Hedvig and Black, Michael and Hastie, Trevor},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Learning and Tracking Cyclic Human Motion},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/ad4cc1fb9b068faecfb70914acc63395-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/ad4cc1fb9b068faecfb70914acc63395-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/ad4cc1fb9b068faecfb70914acc63395-Metadata.json", "review": "", "metareview": "", "pdf_size": 1302494, "gs_citation": 164, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=14874203669982261855&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 21, "aff": "Dept. of Computer Science, Stanford University; Dept. of Computer Science, Brown University; Royal Institute of Technology (KTH), CVAP/NADA; Dept. of Statistics, Stanford University", "aff_domain": "cs.stanford.edu;cs.brown.edu;nada.kth.se;stat.stanford.edu", "email": "cs.stanford.edu;cs.brown.edu;nada.kth.se;stat.stanford.edu", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster", "aff_unique_index": "0;1;2;0", "aff_unique_norm": "Stanford University;Brown University;Royal Institute of Technology (KTH)", "aff_unique_dep": "Department of Computer Science;Dept. of Computer Science;CVAP/NADA", "aff_unique_url": "https://www.stanford.edu;https://www.brown.edu;https://www.kth.se", "aff_unique_abbr": "Stanford;Brown;KTH", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Stanford;", "aff_country_unique_index": "0;0;1;0", "aff_country_unique": "United States;Sweden" }, { "id": "ec6fd83cba", "title": "Machine Learning for Video-Based Rendering", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/958adb57686c2fdec5796398de5f317a-Abstract.html", "author": "Arno Sch\u00f6dl; Irfan A. Essa", "abstract": "We present techniques for rendering and animation of realistic scenes by analyzing and training on short video sequences. This work extends the new paradigm for computer animation, video tex(cid:173) tures, which uses recorded video to generate novel animations by replaying the video samples in a new order. Here we concentrate on video sprites, which are a special type of video texture. In video sprites, instead of storing whole images, the object of inter(cid:173) est is separated from the background and the video samples are stored as a sequence of alpha-matted sprites with associated veloc(cid:173) ity information. They can be rendered anywhere on the screen to create a novel animation of the object. We present methods to cre(cid:173) ate such animations by finding a sequence of sprite samples that is both visually smooth and follows a desired path. To estimate visual smoothness, we train a linear classifier to estimate visual similarity between video samples. If the motion path is known in advance, we use beam search to find a good sample sequence. We can specify the motion interactively by precomputing the sequence cost function using Q-Iearning.", "bibtex": "@inproceedings{NIPS2000_958adb57,\n author = {Sch\\\"{o}dl, Arno and Essa, Irfan},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Machine Learning for Video-Based Rendering},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/958adb57686c2fdec5796398de5f317a-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/958adb57686c2fdec5796398de5f317a-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/958adb57686c2fdec5796398de5f317a-Metadata.json", "review": "", "metareview": "", "pdf_size": 899674, "gs_citation": 43, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=8554565667561366001&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 11, "aff": "GVU Center / College of Computing, Georgia Institute of Technology; GVU Center / College of Computing, Georgia Institute of Technology", "aff_domain": "schoedl.org;cc.gatech.edu", "email": "schoedl.org;cc.gatech.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Georgia Institute of Technology", "aff_unique_dep": "GVU Center / College of Computing", "aff_unique_url": "https://www.gatech.edu", "aff_unique_abbr": "Georgia Tech", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "0b80871212", "title": "Minimum Bayes Error Feature Selection for Continuous Speech Recognition", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/59e0b2658e9f2e77f8d4d83f8d07ca84-Abstract.html", "author": "George Saon; Mukund Padmanabhan", "abstract": "We consider the problem of designing a linear transformation () E lRPx n, of rank p ~ n, which projects the features of a classifier x E lRn onto y = ()x E lRP such as to achieve minimum Bayes error (or probabil(cid:173) ity of misclassification). Two avenues will be explored: the first is to maximize the ()-average divergence between the class densities and the second is to minimize the union Bhattacharyya bound in the range of (). While both approaches yield similar performance in practice, they out(cid:173) perform standard LDA features and show a 10% relative improvement in the word error rate over state-of-the-art cepstral features on a large vocabulary telephony speech recognition task.", "bibtex": "@inproceedings{NIPS2000_59e0b265,\n author = {Saon, George and Padmanabhan, Mukund},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Minimum Bayes Error Feature Selection for Continuous Speech Recognition},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/59e0b2658e9f2e77f8d4d83f8d07ca84-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/59e0b2658e9f2e77f8d4d83f8d07ca84-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/59e0b2658e9f2e77f8d4d83f8d07ca84-Metadata.json", "review": "", "metareview": "", "pdf_size": 967134, "gs_citation": 72, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11162562210586342109&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 7, "aff": ";", "aff_domain": ";", "email": ";", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster" }, { "id": "a1505cfe6b", "title": "Mixtures of Gaussian Processes", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/9fdb62f932adf55af2c0e09e55861964-Abstract.html", "author": "Volker Tresp", "abstract": "We introduce the mixture of Gaussian processes (MGP) model which is useful for applications in which the optimal bandwidth of a map is input dependent. The MGP is derived from the mixture of experts model and can also be used for modeling general conditional probability densities. We discuss how Gaussian processes -in particular in form of Gaussian process classification, the support vector machine and the MGP model(cid:173) can be used for quantifying the dependencies in graphical models.", "bibtex": "@inproceedings{NIPS2000_9fdb62f9,\n author = {Tresp, Volker},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Mixtures of Gaussian Processes},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/9fdb62f932adf55af2c0e09e55861964-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/9fdb62f932adf55af2c0e09e55861964-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/9fdb62f932adf55af2c0e09e55861964-Metadata.json", "review": "", "metareview": "", "pdf_size": 1230649, "gs_citation": 339, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=14408181800685198429&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 14, "aff": "Siemens AG, Corporate Technology, Department of Neural Computation", "aff_domain": "mchp.siemens.de", "email": "mchp.siemens.de", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "Siemens AG", "aff_unique_dep": "Department of Neural Computation", "aff_unique_url": "https://www.siemens.com", "aff_unique_abbr": "Siemens", "aff_country_unique_index": "0", "aff_country_unique": "Germany" }, { "id": "9078905d2b", "title": "Model Complexity, Goodness of Fit and Diminishing Returns", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/69d1fc78dbda242c43ad6590368912d4-Abstract.html", "author": "Igor V. Cadez; Padhraic Smyth", "abstract": "We investigate a general characteristic of the trade-off in learning problems between goodness-of-fit and model complexity. Specifi(cid:173) cally we characterize a general class of learning problems where the goodness-of-fit function can be shown to be convex within first(cid:173) order as a function of model complexity. This general property of \"diminishing returns\" is illustrated on a number of real data sets and learning problems, including finite mixture modeling and multivariate linear regression.", "bibtex": "@inproceedings{NIPS2000_69d1fc78,\n author = {Cadez, Igor and Smyth, Padhraic},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Model Complexity, Goodness of Fit and Diminishing Returns},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/69d1fc78dbda242c43ad6590368912d4-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/69d1fc78dbda242c43ad6590368912d4-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/69d1fc78dbda242c43ad6590368912d4-Metadata.json", "review": "", "metareview": "", "pdf_size": 1268766, "gs_citation": 6, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=6388422002155418417&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 6, "aff": "Information and Computer Science, University of California, Irvine, CA 92697-3425, U.S.A.; Information and Computer Science, University of California, Irvine, CA 92697-3425, U.S.A.", "aff_domain": ";", "email": ";", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "University of California, Irvine", "aff_unique_dep": "Department of Information and Computer Science", "aff_unique_url": "https://www.uci.edu", "aff_unique_abbr": "UCI", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Irvine", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "a85af5f68d", "title": "Modelling Spatial Recall, Mental Imagery and Neglect", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/65fc52ed8f88c81323a418ca94cec2ed-Abstract.html", "author": "Suzanna Becker; Neil Burgess", "abstract": "We present a computational model of the neural mechanisms in the pari(cid:173) etal and temporal lobes that support spatial navigation, recall of scenes and imagery of the products of recall. Long term representations are stored in the hippocampus, and are associated with local spatial and object-related features in the parahippocampal region. Viewer-centered representations are dynamically generated from long term memory in the parietal part of the model. The model thereby simulates recall and im(cid:173) agery of locations and objects in complex environments. After parietal damage, the model exhibits hemispatial neglect in mental imagery that rotates with the imagined perspective of the observer, as in the famous Milan Square experiment [1]. Our model makes novel predictions for the neural representations in the parahippocampal and parietal regions and for behavior in healthy volunteers and neuropsychological patients.", "bibtex": "@inproceedings{NIPS2000_65fc52ed,\n author = {Becker, Suzanna and Burgess, Neil},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Modelling Spatial Recall, Mental Imagery and Neglect},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/65fc52ed8f88c81323a418ca94cec2ed-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/65fc52ed8f88c81323a418ca94cec2ed-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/65fc52ed8f88c81323a418ca94cec2ed-Metadata.json", "review": "", "metareview": "", "pdf_size": 1526055, "gs_citation": 48, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=14521732046888788287&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 15, "aff": "Department of Psychology, McMaster University; Department of Anatomy and Institute of Cognitive Neuroscience, UCL", "aff_domain": "mcmaster.ca;ucl.ac.uk", "email": "mcmaster.ca;ucl.ac.uk", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "McMaster University;University College London", "aff_unique_dep": "Department of Psychology;Department of Anatomy and Institute of Cognitive Neuroscience", "aff_unique_url": "https://www.mcmaster.ca;https://www.ucl.ac.uk", "aff_unique_abbr": "McMaster;UCL", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;1", "aff_country_unique": "Canada;United Kingdom" }, { "id": "19f77eb558", "title": "Multiple Timescales of Adaptation in a Neural Code", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/645098b086d2f9e1e0e939c27f9f2d6f-Abstract.html", "author": "Adrienne L. Fairhall; Geoffrey D. Lewen; William Bialek; Robert R. de Ruyter van Steveninck", "abstract": "Many neural systems extend their dynamic range by adaptation. We ex(cid:173) amine the timescales of adaptation in the context of dynamically mod(cid:173) ulated rapidly-varying stimuli, and demonstrate in the fly visual system that adaptation to the statistical ensemble of the stimulus dynamically maximizes information transmission about the time-dependent stimulus. Further, while the rate response has long transients, the adaptation takes place on timescales consistent with optimal variance estimation.", "bibtex": "@inproceedings{NIPS2000_645098b0,\n author = {Fairhall, Adrienne and Lewen, Geoffrey and Bialek, William and van Steveninck, Robert},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Multiple Timescales of Adaptation in a Neural Code},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/645098b086d2f9e1e0e939c27f9f2d6f-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/645098b086d2f9e1e0e939c27f9f2d6f-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/645098b086d2f9e1e0e939c27f9f2d6f-Metadata.json", "review": "", "metareview": "", "pdf_size": 1396277, "gs_citation": 41, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=15566657285966419069&as_sdt=400005&sciodt=0,14&hl=en", "gs_version_total": 11, "aff": ";;;", "aff_domain": ";;;", "email": ";;;", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster" }, { "id": "45f72bd47a", "title": "Natural Sound Statistics and Divisive Normalization in the Auditory System", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/96c5c28becf18e71190460a9955aa4d8-Abstract.html", "author": "Odelia Schwartz; Eero P. Simoncelli", "abstract": "We explore the statistical properties of natural sound stimuli pre(cid:173) processed with a bank of linear filters. The responses of such filters exhibit a striking form of statistical dependency, in which the response variance of each filter grows with the response amplitude of filters tuned for nearby frequencies. These dependencies may be substantially re(cid:173) duced using an operation known as divisive normalization, in which the response of each filter is divided by a weighted sum of the recti(cid:173) fied responses of other filters. The weights may be chosen to maximize the independence of the normalized responses for an ensemble of natu(cid:173) ral sounds. We demonstrate that the resulting model accounts for non(cid:173) linearities in the response characteristics of the auditory nerve, by com(cid:173) paring model simulations to electrophysiological recordings. In previous work (NIPS, 1998) we demonstrated that an analogous model derived from the statistics of natural images accounts for non-linear properties of neurons in primary visual cortex. Thus, divisive normalization appears to be a generic mechanism for eliminating a type of statistical dependency that is prevalent in natural signals of different modalities.", "bibtex": "@inproceedings{NIPS2000_96c5c28b,\n author = {Schwartz, Odelia and Simoncelli, Eero},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Natural Sound Statistics and Divisive Normalization in the Auditory System},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/96c5c28becf18e71190460a9955aa4d8-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/96c5c28becf18e71190460a9955aa4d8-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/96c5c28becf18e71190460a9955aa4d8-Metadata.json", "review": "", "metareview": "", "pdf_size": 1246843, "gs_citation": 56, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=3558451985144816579&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 13, "aff": "Center for Neural Science, New York University; Howard Hughes Medical Institute + Center for Neural Science + Courant Institute of Mathematical Sciences, New York University", "aff_domain": "cns.nyu.edu;nyu.edu", "email": "cns.nyu.edu;nyu.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1+0+0", "aff_unique_norm": "New York University;Howard Hughes Medical Institute", "aff_unique_dep": "Center for Neural Science;", "aff_unique_url": "https://www.nyu.edu;https://www.hhmi.org", "aff_unique_abbr": "NYU;HHMI", "aff_campus_unique_index": "0;0", "aff_campus_unique": "New York;", "aff_country_unique_index": "0;0+0+0", "aff_country_unique": "United States" }, { "id": "56dfeb5642", "title": "New Approaches Towards Robust and Adaptive Speech Recognition", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/cb79f8fa58b91d3af6c9c991f63962d3-Abstract.html", "author": "Herv\u00e9 Bourlard; Samy Bengio; Katrin Weber", "abstract": "In this paper, we discuss some new research directions in automatic speech recognition (ASR), and which somewhat deviate from the usual approaches. More specifically, we will motivate and briefly describe new approaches based on multi-stream and multi/band ASR. These approaches extend the standard hidden Markov model (HMM) based approach by assuming that the different (frequency) channels representing the speech signal are processed by different (independent) \"experts\", each expert focusing on a different char(cid:173) acteristic of the signal, and that the different stream likelihoods (or posteriors) are combined at some (temporal) stage to yield a global recognition output. As a further extension to multi-stream ASR, we will finally introduce a new approach, referred to as HMM2, where the HMM emission probabilities are estimated via state spe(cid:173) cific feature based HMMs responsible for merging the stream infor(cid:173) mation and modeling their possible correlation.", "bibtex": "@inproceedings{NIPS2000_cb79f8fa,\n author = {Bourlard, Herv\\'{e} and Bengio, Samy and Weber, Katrin},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {New Approaches Towards Robust and Adaptive Speech Recognition},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/cb79f8fa58b91d3af6c9c991f63962d3-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/cb79f8fa58b91d3af6c9c991f63962d3-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/cb79f8fa58b91d3af6c9c991f63962d3-Metadata.json", "review": "", "metareview": "", "pdf_size": 826999, "gs_citation": 5, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=13277974115505272878&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 15, "aff": ";;", "aff_domain": ";;", "email": ";;", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster" }, { "id": "8b10c61f3f", "title": "Noise Suppression Based on Neurophysiologically-motivated SNR Estimation for Robust Speech Recognition", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/fc4ddc15f9f4b4b06ef7844d6bb53abf-Abstract.html", "author": "J\u00fcrgen Tchorz; Michael Kleinschmidt; Birger Kollmeier", "abstract": "A novel noise suppression scheme for speech signals is proposed which is based on a neurophysiologically-motivated estimation of the local signal-to-noise ratio (SNR) in different frequency chan(cid:173) nels. For SNR-estimation, the input signal is transformed into so-called Amplitude Modulation Spectrograms (AMS), which rep(cid:173) resent both spectral and temporal characteristics of the respective analysis frame, and which imitate the representation of modula(cid:173) tion frequencies in higher stages of the mammalian auditory sys(cid:173) tem. A neural network is used to analyse AMS patterns generated from noisy speech and estimates the local SNR. Noise suppres(cid:173) sion is achieved by attenuating frequency channels according to their SNR. The noise suppression algorithm is evaluated in speaker(cid:173) independent digit recognition experiments and compared to noise suppression by Spectral Subtraction.", "bibtex": "@inproceedings{NIPS2000_fc4ddc15,\n author = {Tchorz, J\\\"{u}rgen and Kleinschmidt, Michael and Kollmeier, Birger},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Noise Suppression Based on Neurophysiologically-motivated SNR Estimation for Robust Speech Recognition},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/fc4ddc15f9f4b4b06ef7844d6bb53abf-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/fc4ddc15f9f4b4b06ef7844d6bb53abf-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/fc4ddc15f9f4b4b06ef7844d6bb53abf-Metadata.json", "review": "", "metareview": "", "pdf_size": 1340540, "gs_citation": 8, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11074674418998900888&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 7, "aff": "Medical Physics Group, Oldenburg University, 26111 Oldenburg, Germany; Medical Physics Group, Oldenburg University, 26111 Oldenburg, Germany; Medical Physics Group, Oldenburg University, 26111 Oldenburg, Germany", "aff_domain": "medi.physik.uni-oldenburg.de; ; ", "email": "medi.physik.uni-oldenburg.de; ; ", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0", "aff_unique_norm": "Oldenburg University", "aff_unique_dep": "Medical Physics Group", "aff_unique_url": "https://www.uni-oldenburg.de", "aff_unique_abbr": "", "aff_campus_unique_index": "0;0;0", "aff_campus_unique": "Oldenburg", "aff_country_unique_index": "0;0;0", "aff_country_unique": "Germany" }, { "id": "af7d7d2596", "title": "Occam's Razor", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/0950ca92a4dcf426067cfd2246bb5ff3-Abstract.html", "author": "Carl Edward Rasmussen; Zoubin Ghahramani", "abstract": "The Bayesian paradigm apparently only sometimes gives rise to Occam's Razor; at other times very large models perform well. We give simple examples of both kinds of behaviour. The two views are reconciled when measuring complexity of functions, rather than of the machinery used to implement them. We analyze the complexity of functions for some linear in the parameter models that are equivalent to Gaussian Processes, and always find Occam's Razor at work.", "bibtex": "@inproceedings{NIPS2000_0950ca92,\n author = {Rasmussen, Carl and Ghahramani, Zoubin},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Occam\\textquotesingle s Razor},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/0950ca92a4dcf426067cfd2246bb5ff3-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/0950ca92a4dcf426067cfd2246bb5ff3-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/0950ca92a4dcf426067cfd2246bb5ff3-Metadata.json", "review": "", "metareview": "", "pdf_size": 1209293, "gs_citation": 1628, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11895938102761137877&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 7, "aff": "Department of Mathematical Modelling, Technical University of Denmark; Gatsby Computational Neuroscience Unit, University College London", "aff_domain": "imm.dtu.dk;gatsby.ucl.ac.uk", "email": "imm.dtu.dk;gatsby.ucl.ac.uk", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Technical University of Denmark;University College London", "aff_unique_dep": "Department of Mathematical Modelling;Gatsby Computational Neuroscience Unit", "aff_unique_url": "https://www.teknologisk.dk;https://www.ucl.ac.uk", "aff_unique_abbr": "DTU;UCL", "aff_campus_unique_index": "1", "aff_campus_unique": ";London", "aff_country_unique_index": "0;1", "aff_country_unique": "Denmark;United Kingdom" }, { "id": "c473e3105f", "title": "On Iterative Krylov-Dogleg Trust-Region Steps for Solving Neural Networks Nonlinear Least Squares Problems", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/7ffd85d93a3e4de5c490d304ccd9f864-Abstract.html", "author": "Eiji Mizutani; James Demmel", "abstract": "This paper describes a method of dogleg trust-region steps, or re(cid:173) stricted Levenberg-Marquardt steps, based on a projection pro(cid:173) cess onto the Krylov subspaces for neural networks nonlinear least squares problems. In particular, the linear conjugate gradient (CG) method works as the inner iterative algorithm for solving the lin(cid:173) earized Gauss-Newton normal equation, whereas the outer nonlin(cid:173) ear algorithm repeatedly takes so-called \"Krylov-dogleg\" steps, re(cid:173) lying only on matrix-vector multiplication without explicitly form(cid:173) ing the Jacobian matrix or the Gauss-Newton model Hessian. That is, our iterative dogleg algorithm can reduce both operational counts and memory space by a factor of O(n) (the number of pa(cid:173) rameters) in comparison with a direct linear-equation solver. This memory-less property is useful for large-scale problems.", "bibtex": "@inproceedings{NIPS2000_7ffd85d9,\n author = {Mizutani, Eiji and Demmel, James},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {On Iterative Krylov-Dogleg Trust-Region Steps for Solving Neural Networks Nonlinear Least Squares Problems},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/7ffd85d93a3e4de5c490d304ccd9f864-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/7ffd85d93a3e4de5c490d304ccd9f864-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/7ffd85d93a3e4de5c490d304ccd9f864-Metadata.json", "review": "", "metareview": "", "pdf_size": 1295228, "gs_citation": 13, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=2959716710274845708&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 10, "aff": "Department of Computer Science, National Tsing Hua University, Hsinchu, 30043 TAIWAN R.O.C.; Mathematics and Computer Science, University of California at Berkeley, Berkeley, CA 94720 USA", "aff_domain": "wayne.cs.nthu.edu.tw;cs.berkeley.edu", "email": "wayne.cs.nthu.edu.tw;cs.berkeley.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "National Tsing Hua University;University of California, Berkeley", "aff_unique_dep": "Department of Computer Science;Department of Mathematics and Computer Science", "aff_unique_url": "https://www.nthu.edu.tw;https://www.berkeley.edu", "aff_unique_abbr": "NTHU;UC Berkeley", "aff_campus_unique_index": "0;1", "aff_campus_unique": "Taiwan;Berkeley", "aff_country_unique_index": "0;1", "aff_country_unique": "China;United States" }, { "id": "ebae087d9e", "title": "On Reversing Jensen's Inequality", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/44a2e0804995faf8d2e3b084a1e2db1d-Abstract.html", "author": "Tony Jebara; Alex Pentland", "abstract": "Jensen's inequality is a powerful mathematical tool and one of the workhorses in statistical learning. Its applications therein include the EM algorithm, Bayesian estimation and Bayesian inference. Jensen com(cid:173) putes simple lower bounds on otherwise intractable quantities such as products of sums and latent log-likelihoods. This simplification then per(cid:173) mits operations like integration and maximization. Quite often (i.e. in discriminative learning) upper bounds are needed as well. We derive and prove an efficient analytic inequality that provides such variational upper bounds. This inequality holds for latent variable mixtures of exponential family distributions and thus spans a wide range of contemporary statis(cid:173) tical models. We also discuss applications of the upper bounds including maximum conditional likelihood, large margin discriminative models and conditional Bayesian inference. Convergence, efficiency and prediction results are shown. 1", "bibtex": "@inproceedings{NIPS2000_44a2e080,\n author = {Jebara, Tony and Pentland, Alex},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {On Reversing Jensen\\textquotesingle s Inequality},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/44a2e0804995faf8d2e3b084a1e2db1d-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/44a2e0804995faf8d2e3b084a1e2db1d-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/44a2e0804995faf8d2e3b084a1e2db1d-Metadata.json", "review": "", "metareview": "", "pdf_size": 1258739, "gs_citation": 68, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=6875014352026618000&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 13, "aff": ";", "aff_domain": ";", "email": ";", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster" }, { "id": "92c5621839", "title": "On a Connection between Kernel PCA and Metric Multidimensional Scaling", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/d4b2aeb2453bdadaa45cbe9882ffefcf-Abstract.html", "author": "Christopher K. I. Williams", "abstract": "In this paper we show that the kernel peA algorithm of Sch6lkopf et al (1998) can be interpreted as a form of metric multidimensional scaling (MDS) when the kernel function k(x, y) is isotropic, i.e. it depends only on Ilx - yll. This leads to a metric MDS algorithm where the desired configuration of points is found via the solution of an eigenproblem rather than through the iterative optimization of the stress objective function. The question of kernel choice is also discussed.", "bibtex": "@inproceedings{NIPS2000_d4b2aeb2,\n author = {Williams, Christopher},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {On a Connection between Kernel PCA and Metric Multidimensional Scaling},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/d4b2aeb2453bdadaa45cbe9882ffefcf-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/d4b2aeb2453bdadaa45cbe9882ffefcf-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/d4b2aeb2453bdadaa45cbe9882ffefcf-Metadata.json", "review": "", "metareview": "", "pdf_size": 1333639, "gs_citation": 244, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=7487777910546086478&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 15, "aff": "Division of Informatics, The University of Edinburgh", "aff_domain": "ed.ac.uk", "email": "ed.ac.uk", "github": "", "project": "http://anc.ed.ac.uk", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "University of Edinburgh", "aff_unique_dep": "Division of Informatics", "aff_unique_url": "https://www.ed.ac.uk", "aff_unique_abbr": "Edinburgh", "aff_campus_unique_index": "0", "aff_campus_unique": "Edinburgh", "aff_country_unique_index": "0", "aff_country_unique": "United Kingdom" }, { "id": "72b76a27a0", "title": "One Microphone Source Separation", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/d523773c6b194f37b938d340d5d02232-Abstract.html", "author": "Sam T. Roweis", "abstract": "Source separation, or computational auditory scene analysis , attempts to extract individual acoustic objects from input which contains a mixture of sounds from different sources, altered by the acoustic environment. Unmixing algorithms such as lCA and its extensions recover sources by reweighting multiple obser(cid:173) vation sequences, and thus cannot operate when only a single observation signal is available. I present a technique called refiltering which recovers sources by a nonstationary reweighting (\"masking\") of frequency sub-bands from a single recording, and argue for the application of statistical algorithms to learning this masking function . I present results of a simple factorial HMM system which learns on recordings of single speakers and can then separate mixtures using only one observation signal by computing the masking function and then refiltering.", "bibtex": "@inproceedings{NIPS2000_d523773c,\n author = {Roweis, Sam},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {One Microphone Source Separation},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/d523773c6b194f37b938d340d5d02232-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/d523773c6b194f37b938d340d5d02232-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/d523773c6b194f37b938d340d5d02232-Metadata.json", "review": "", "metareview": "", "pdf_size": 1517432, "gs_citation": 620, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=10160791171319499892&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 16, "aff": "Gatsby Unit, University College London", "aff_domain": "gatsby.ucl.ac.uk", "email": "gatsby.ucl.ac.uk", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "University College London", "aff_unique_dep": "Gatsby Unit", "aff_unique_url": "https://www.ucl.ac.uk", "aff_unique_abbr": "UCL", "aff_campus_unique_index": "0", "aff_campus_unique": "London", "aff_country_unique_index": "0", "aff_country_unique": "United Kingdom" }, { "id": "798c3ebcfb", "title": "Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early Stopping", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/059fdcd96baeb75112f09fa1dcc740cc-Abstract.html", "author": "Rich Caruana; Steve Lawrence; C. Lee Giles", "abstract": "The conventional wisdom is that backprop nets with excess hidden units generalize poorly. We show that nets with excess capacity generalize well when trained with backprop and early stopping. Experiments sug(cid:173) gest two reasons for this: 1) Overfitting can vary significantly in different regions of the model. Excess capacity allows better fit to regions of high non-linearity, and backprop often avoids overfitting the regions of low non-linearity. 2) Regardless of size, nets learn task subcomponents in similar sequence. Big nets pass through stages similar to those learned by smaller nets. Early stopping can stop training the large net when it generalizes comparably to a smaller net. We also show that conjugate gradient can yield worse generalization because it overfits regions of low non-linearity when learning to fit regions of high non-linearity.", "bibtex": "@inproceedings{NIPS2000_059fdcd9,\n author = {Caruana, Rich and Lawrence, Steve and Giles, C.},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early Stopping},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/059fdcd96baeb75112f09fa1dcc740cc-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/059fdcd96baeb75112f09fa1dcc740cc-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/059fdcd96baeb75112f09fa1dcc740cc-Metadata.json", "review": "", "metareview": "", "pdf_size": 1299708, "gs_citation": 1742, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=10546806692349897362&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 17, "aff": "CALD,CMU; NEC Research Institute; Information Sciences, Penn State University", "aff_domain": "cs.cmu.edu;research.nj.nec.com;ist.psu.edu", "email": "cs.cmu.edu;research.nj.nec.com;ist.psu.edu", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;1;2", "aff_unique_norm": "Carnegie Mellon University;NEC Research Institute;Penn State University", "aff_unique_dep": ";;Information Sciences", "aff_unique_url": "https://www.cmu.edu;https://www.neclab.eu;https://www.psu.edu", "aff_unique_abbr": "CMU;NEC RI;PSU", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "9c0444cc71", "title": "Partially Observable SDE Models for Image Sequence Recognition Tasks", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f26dab9bf6a137c3b6782e562794c2f2-Abstract.html", "author": "Javier R. Movellan; Paul Mineiro; Ruth J. Williams", "abstract": "This paper explores a framework for recognition of image sequences using partially observable stochastic differential equation (SDE) models. Monte-Carlo importance sampling techniques are used for efficient estimation of sequence likelihoods and sequence likelihood gradients. Once the network dynamics are learned, we apply the SDE models to sequence recognition tasks in a manner similar to the way Hidden Markov models (HMMs) are commonly applied. The potential advantage of SDEs over HMMS is the use of contin(cid:173) uous state dynamics. We present encouraging results for a video sequence recognition task in which SDE models provided excellent performance when compared to hidden Markov models.", "bibtex": "@inproceedings{NIPS2000_f26dab9b,\n author = {Movellan, Javier and Mineiro, Paul and Williams, Ruth},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Partially Observable SDE Models for Image Sequence Recognition Tasks},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f26dab9bf6a137c3b6782e562794c2f2-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f26dab9bf6a137c3b6782e562794c2f2-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f26dab9bf6a137c3b6782e562794c2f2-Metadata.json", "review": "", "metareview": "", "pdf_size": 1326258, "gs_citation": 6, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=8247449329336568534&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 5, "aff": ";;", "aff_domain": ";;", "email": ";;", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster" }, { "id": "a4900ec418", "title": "Periodic Component Analysis: An Eigenvalue Method for Representing Periodic Structure in Speech", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f22e4747da1aa27e363d86d40ff442fe-Abstract.html", "author": "Lawrence K. Saul; Jont B. Allen", "abstract": "An eigenvalue method is developed for analyzing periodic structure in speech. Signals are analyzed by a matrix diagonalization reminiscent of methods for principal component analysis (PCA) and independent com(cid:173) ponent analysis (ICA). Our method-called periodic component analysis (1l\"CA)-uses constructive interference to enhance periodic components of the frequency spectrum and destructive interference to cancel noise. The front end emulates important aspects of auditory processing, such as cochlear filtering, nonlinear compression, and insensitivity to phase, with the aim of approaching the robustness of human listeners. The method avoids the inefficiencies of autocorrelation at the pitch period: it does not require long delay lines, and it correlates signals at a clock rate on the order of the actual pitch, as opposed to the original sampling rate. We derive its cost function and present some experimental results.", "bibtex": "@inproceedings{NIPS2000_f22e4747,\n author = {Saul, Lawrence and Allen, Jont},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Periodic Component Analysis: An Eigenvalue Method for Representing Periodic Structure in Speech},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f22e4747da1aa27e363d86d40ff442fe-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f22e4747da1aa27e363d86d40ff442fe-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f22e4747da1aa27e363d86d40ff442fe-Metadata.json", "review": "", "metareview": "", "pdf_size": 1441633, "gs_citation": 74, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=2721843397297067031&as_sdt=400005&sciodt=0,14&hl=en", "gs_version_total": 11, "aff": "AT&T Labs, 180 Park Ave, Florham Park, NJ 07932; AT&T Labs, 180 Park Ave, Florham Park, NJ 07932", "aff_domain": "research.att.com;research.att.com", "email": "research.att.com;research.att.com", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "AT&T Labs", "aff_unique_dep": "", "aff_unique_url": "https://www.att.com/labs", "aff_unique_abbr": "AT&T Labs", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "3bd729c2f3", "title": "Permitted and Forbidden Sets in Symmetric Threshold-Linear Networks", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/c8cbd669cfb2f016574e9d147092b5bb-Abstract.html", "author": "Richard H. R. Hahnloser; H. Sebastian Seung", "abstract": "Ascribing computational principles to neural feedback circuits is an important problem in theoretical neuroscience. We study symmet(cid:173) ric threshold-linear networks and derive stability results that go beyond the insights that can be gained from Lyapunov theory or energy functions. By applying linear analysis to subnetworks com(cid:173) posed of coactive neurons, we determine the stability of potential steady states. We find that stability depends on two types of eigen(cid:173) modes. One type determines global stability and the other type determines whether or not multistability is possible. We can prove the equivalence of our stability criteria with criteria taken from quadratic programming. Also, we show that there are permitted sets of neurons that can be coactive at a steady state and forbid(cid:173) den sets that cannot. Permitted sets are clustered in the sense that subsets of permitted sets are permitted and supersets of forbidden sets are forbidden. By viewing permitted sets as memories stored in the synaptic connections, we can provide a formulation of long(cid:173) term memory that is more general than the traditional perspective of fixed point attractor networks.", "bibtex": "@inproceedings{NIPS2000_c8cbd669,\n author = {Hahnloser, Richard and Seung, H. Sebastian},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Permitted and Forbidden Sets in Symmetric Threshold-Linear Networks},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/c8cbd669cfb2f016574e9d147092b5bb-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/c8cbd669cfb2f016574e9d147092b5bb-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/c8cbd669cfb2f016574e9d147092b5bb-Metadata.json", "review": "", "metareview": "", "pdf_size": 1384687, "gs_citation": 330, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=12435045844328661159&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 19, "aff": "Dept. of Brain & Cog. Sci., MIT; Dept. of Brain & Cog. Sci., MIT", "aff_domain": "ai.mit.edu;mit.edu", "email": "ai.mit.edu;mit.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Massachusetts Institute of Technology", "aff_unique_dep": "Department of Brain and Cognitive Sciences", "aff_unique_url": "https://web.mit.edu", "aff_unique_abbr": "MIT", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Cambridge", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "0e951b148a", "title": "Place Cells and Spatial Navigation Based on 2D Visual Feature Extraction, Path Integration, and Reinforcement Learning", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/cd14821dab219ea06e2fd1a2df2e3582-Abstract.html", "author": "Angelo Arleo; Fabrizio Smeraldi; St\u00e9phane Hug; Wulfram Gerstner", "abstract": "We model hippocampal place cells and head-direction cells by combin(cid:173) ing allothetic (visual) and idiothetic (proprioceptive) stimuli. Visual in(cid:173) put, provided by a video camera on a miniature robot, is preprocessed by a set of Gabor filters on 31 nodes of a log-polar retinotopic graph. Unsu(cid:173) pervised Hebbian learning is employed to incrementally build a popula(cid:173) tion of localized overlapping place fields. Place cells serve as basis func(cid:173) tions for reinforcement learning. Experimental results for goal-oriented navigation of a mobile robot are presented.", "bibtex": "@inproceedings{NIPS2000_cd14821d,\n author = {Arleo, Angelo and Smeraldi, Fabrizio and Hug, St\\'{e}phane and Gerstner, Wulfram},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Place Cells and Spatial Navigation Based on 2D Visual Feature Extraction, Path Integration, and Reinforcement Learning},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/cd14821dab219ea06e2fd1a2df2e3582-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/cd14821dab219ea06e2fd1a2df2e3582-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/cd14821dab219ea06e2fd1a2df2e3582-Metadata.json", "review": "", "metareview": "", "pdf_size": 1408015, "gs_citation": 42, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11892550701580580238&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 14, "aff": "Centre for Neuro-Mimetic Systems, MANTRA Swiss Federal Institute of Technology Lausanne, CH-1015 Lausanne EPFL, Switzerland; Centre for Neuro-Mimetic Systems, MANTRA Swiss Federal Institute of Technology Lausanne, CH-1015 Lausanne EPFL, Switzerland; Centre for Neuro-Mimetic Systems, MANTRA Swiss Federal Institute of Technology Lausanne, CH-1015 Lausanne EPFL, Switzerland; Centre for Neuro-Mimetic Systems, MANTRA Swiss Federal Institute of Technology Lausanne, CH-1015 Lausanne EPFL, Switzerland", "aff_domain": "epji.ch; ; ; ", "email": "epji.ch; ; ; ", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0;0", "aff_unique_norm": "Swiss Federal Institute of Technology Lausanne", "aff_unique_dep": "Centre for Neuro-Mimetic Systems", "aff_unique_url": "https://www.epfl.ch", "aff_unique_abbr": "EPFL", "aff_campus_unique_index": "0;0;0;0", "aff_campus_unique": "Lausanne", "aff_country_unique_index": "0;0;0;0", "aff_country_unique": "Switzerland" }, { "id": "86c0f1c9db", "title": "Position Variance, Recurrence and Perceptual Learning", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/c45008212f7bdf6eab6050c2a564435a-Abstract.html", "author": "Zhaoping Li; Peter Dayan", "abstract": "Stimulus arrays are inevitably presented at different positions on the retina in visual tasks, even those that nominally require fixation. In par(cid:173) ticular, this applies to many perceptual learning tasks. We show that per(cid:173) ceptual inference or discrimination in the face of positional variance has a structurally different quality from inference about fixed position stimuli, involving a particular, quadratic, non-linearity rather than a purely lin(cid:173) ear discrimination. We show the advantage taking this non-linearity into account has for discrimination, and suggest it as a role for recurrent con(cid:173) nections in area VI, by demonstrating the superior discrimination perfor(cid:173) mance of a recurrent network. We propose that learning the feedforward and recurrent neural connections for these tasks corresponds to the fast and slow components of learning observed in perceptual learning tasks.", "bibtex": "@inproceedings{NIPS2000_c4500821,\n author = {Li, Zhaoping and Dayan, Peter},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Position Variance, Recurrence and Perceptual Learning},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/c45008212f7bdf6eab6050c2a564435a-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/c45008212f7bdf6eab6050c2a564435a-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/c45008212f7bdf6eab6050c2a564435a-Metadata.json", "review": "", "metareview": "", "pdf_size": 1370735, "gs_citation": 2, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=6164761967339806371&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 14, "aff": ";", "aff_domain": ";", "email": ";", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster" }, { "id": "4d4a3508b3", "title": "Probabilistic Semantic Video Indexing", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/52d2752b150f9c35ccb6869cbf074e48-Abstract.html", "author": "Milind R. Naphade; Igor Kozintsev; Thomas S. Huang", "abstract": "We propose a novel probabilistic framework for semantic video in(cid:173) dexing. We define probabilistic multimedia objects (multijects) to map low-level media features to high-level semantic labels. A graphical network of such multijects (multinet) captures scene con(cid:173) text by discovering intra-frame as well as inter-frame dependency relations between the concepts. The main contribution is a novel application of a factor graph framework to model this network. We model relations between semantic concepts in terms of their co-occurrence as well as the temporal dependencies between these concepts within video shots. Using the sum-product algorithm [1] for approximate or exact inference in these factor graph multinets, we attempt to correct errors made during isolated concept detec(cid:173) tion by forcing high-level constraints. This results in a significant improvement in the overall detection performance.", "bibtex": "@inproceedings{NIPS2000_52d2752b,\n author = {Naphade, Milind and Kozintsev, Igor and Huang, Thomas S},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Probabilistic Semantic Video Indexing},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/52d2752b150f9c35ccb6869cbf074e48-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/52d2752b150f9c35ccb6869cbf074e48-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/52d2752b150f9c35ccb6869cbf074e48-Metadata.json", "review": "", "metareview": "", "pdf_size": 1337563, "gs_citation": 31, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=9007694911226121170&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 6, "aff": "Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign; Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign; Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign", "aff_domain": "ifp.uiuc.edu;ifp.uiuc.edu;ifp.uiuc.edu", "email": "ifp.uiuc.edu;ifp.uiuc.edu;ifp.uiuc.edu", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0", "aff_unique_norm": "University of Illinois Urbana-Champaign", "aff_unique_dep": "Department of Electrical and Computer Engineering", "aff_unique_url": "https://illinois.edu", "aff_unique_abbr": "UIUC", "aff_campus_unique_index": "0;0;0", "aff_campus_unique": "Urbana-Champaign", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "0fb143c9cf", "title": "Processing of Time Series by Neural Circuits with Biologically Realistic Synaptic Dynamics", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/944626adf9e3b76a3919b50dc0b080a4-Abstract.html", "author": "Thomas Natschl\u00e4ger; Wolfgang Maass; Eduardo D. Sontag; Anthony M. Zador", "abstract": "Experimental data show that biological synapses behave quite differently from the symbolic synapses in common artificial neural network models. Biological synapses are dynamic, i.e., their \"weight\" changes on a short time scale by several hundred percent in dependence of the past input to the synapse. In this article we explore the consequences that these synaptic dynamics entail for the computational power of feedforward neural networks. We show that gradient descent suffices to approximate a given (quadratic) filter by a rather small neural system with dynamic synapses. We also compare our network model to artificial neural net(cid:173) works designed for time series processing. Our numerical results are complemented by theoretical analysis which show that even with just a single hidden layer such networks can approximate a surprisingly large large class of nonlinear filters: all filters that can be characterized by Volterra series. This result is robust with regard to various changes in the model for synaptic dynamics.", "bibtex": "@inproceedings{NIPS2000_944626ad,\n author = {Natschl\\\"{a}ger, Thomas and Maass, Wolfgang and Sontag, Eduardo and Zador, Anthony},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Processing of Time Series by Neural Circuits with Biologically Realistic Synaptic Dynamics},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/944626adf9e3b76a3919b50dc0b080a4-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/944626adf9e3b76a3919b50dc0b080a4-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/944626adf9e3b76a3919b50dc0b080a4-Metadata.json", "review": "", "metareview": "", "pdf_size": 1349347, "gs_citation": 4, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=12802425216112735933&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 22, "aff": "Institute for Theoretical Computer Science, Technische Universitat Graz, Austria; Institute for Theoretical Computer Science, Technische Universitat Graz, Austria; Dept. of Mathematics, Rutgers University, New Brunswick, NJ 08903, USA; Cold Spring Harbor Laboratory, 1 Bungtown Rd, Cold Spring Harbor, NY 11724", "aff_domain": "igi.tu-graz.ac.at;igi.tu-graz.ac.at;hilbert.rutgers.edu;cshl.org", "email": "igi.tu-graz.ac.at;igi.tu-graz.ac.at;hilbert.rutgers.edu;cshl.org", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster", "aff_unique_index": "0;0;1;2", "aff_unique_norm": "Technische Universitat Graz;Rutgers University;Cold Spring Harbor Laboratory", "aff_unique_dep": "Institute for Theoretical Computer Science;Dept. of Mathematics;", "aff_unique_url": "https://www.tugraz.at;https://www.rutgers.edu;https://www.cshl.edu", "aff_unique_abbr": ";Rutgers;CSHL", "aff_campus_unique_index": "1;2", "aff_campus_unique": ";New Brunswick;Cold Spring Harbor", "aff_country_unique_index": "0;0;1;1", "aff_country_unique": "Austria;United States" }, { "id": "600bf25c5f", "title": "Programmable Reinforcement Learning Agents", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/11108a3dbfe4636cb40b84b803b2fff6-Abstract.html", "author": "David Andre; Stuart J. Russell", "abstract": "We present an expressive agent design language for reinforcement learn(cid:173) ing that allows the user to constrain the policies considered by the learn(cid:173) ing process.The language includes standard features such as parameter(cid:173) ized subroutines, temporary interrupts, aborts, and memory variables, but also allows for unspecified choices in the agent program. For learning that which isn't specified, we present provably convergent learning algo(cid:173) rithms. We demonstrate by example that agent programs written in the language are concise as well as modular. This facilitates state abstraction and the transferability of learned skills.", "bibtex": "@inproceedings{NIPS2000_11108a3d,\n author = {Andre, David and Russell, Stuart},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Programmable Reinforcement Learning Agents},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/11108a3dbfe4636cb40b84b803b2fff6-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/11108a3dbfe4636cb40b84b803b2fff6-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/11108a3dbfe4636cb40b84b803b2fff6-Metadata.json", "review": "", "metareview": "", "pdf_size": 1492017, "gs_citation": 181, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=3505842626923951476&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 26, "aff": "Computer Science Division, UC Berkeley, CA 94702; Computer Science Division, UC Berkeley, CA 94702", "aff_domain": "cs.berkeley.edu;cs.berkeley.edu", "email": "cs.berkeley.edu;cs.berkeley.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "University of California, Berkeley", "aff_unique_dep": "Computer Science Division", "aff_unique_url": "https://www.berkeley.edu", "aff_unique_abbr": "UC Berkeley", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Berkeley", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "13a97134b7", "title": "Propagation Algorithms for Variational Bayesian Learning", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/77369e37b2aa1404f416275183ab055f-Abstract.html", "author": "Zoubin Ghahramani; Matthew J. Beal", "abstract": "Variational approximations are becoming a widespread tool for Bayesian learning of graphical models. We provide some theoret(cid:173) ical results for the variational updates in a very general family of conjugate-exponential graphical models. We show how the belief propagation and the junction tree algorithms can be used in the inference step of variational Bayesian learning. Applying these re(cid:173) sults to the Bayesian analysis of linear-Gaussian state-space models we obtain a learning procedure that exploits the Kalman smooth(cid:173) ing propagation, while integrating over all model parameters. We demonstrate how this can be used to infer the hidden state dimen(cid:173) sionality of the state-space model in a variety of synthetic problems and one real high-dimensional data set.", "bibtex": "@inproceedings{NIPS2000_77369e37,\n author = {Ghahramani, Zoubin and Beal, Matthew},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Propagation Algorithms for Variational Bayesian Learning},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/77369e37b2aa1404f416275183ab055f-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/77369e37b2aa1404f416275183ab055f-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/77369e37b2aa1404f416275183ab055f-Metadata.json", "review": "", "metareview": "", "pdf_size": 1522038, "gs_citation": 462, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=14452063863324445502&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 16, "aff": ";", "aff_domain": ";", "email": ";", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster" }, { "id": "3453303334", "title": "Rate-coded Restricted Boltzmann Machines for Face Recognition", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/c366c2c97d47b02b24c3ecade4c40a01-Abstract.html", "author": "Yee Whye Teh; Geoffrey E. Hinton", "abstract": "We describe a neurally-inspired, unsupervised learning algorithm that builds a non-linear generative model for pairs of face images from the same individual. Individuals are then recognized by finding the highest relative probability pair among all pairs that consist of a test image and an image whose identity is known. Our method compares favorably with other methods in the literature. The generative model consists of a single layer of rate-coded, non-linear feature detectors and it has the property that, given a data vector, the true posterior probability distribution over the feature detector activities can be inferred rapidly without iteration or approximation. The weights of the feature detectors are learned by com(cid:173) paring the correlations of pixel intensities and feature activations in two phases: When the network is observing real data and when it is observing reconstructions of real data generated from the feature activations.", "bibtex": "@inproceedings{NIPS2000_c366c2c9,\n author = {Teh, Yee Whye and Hinton, Geoffrey E},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Rate-coded Restricted Boltzmann Machines for Face Recognition},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/c366c2c97d47b02b24c3ecade4c40a01-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/c366c2c97d47b02b24c3ecade4c40a01-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/c366c2c97d47b02b24c3ecade4c40a01-Metadata.json", "review": "", "metareview": "", "pdf_size": 1362269, "gs_citation": 219, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=2053891185703460398&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 17, "aff": "Department of Computer Science, University of Toronto; Gatsby Computational Neuroscience Unit, University College London", "aff_domain": "cs.toronto.edu;gatsby.ucl.ac.uk", "email": "cs.toronto.edu;gatsby.ucl.ac.uk", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "University of Toronto;University College London", "aff_unique_dep": "Department of Computer Science;Gatsby Computational Neuroscience Unit", "aff_unique_url": "https://www.utoronto.ca;https://www.ucl.ac.uk", "aff_unique_abbr": "U of T;UCL", "aff_campus_unique_index": "0;1", "aff_campus_unique": "Toronto;London", "aff_country_unique_index": "0;1", "aff_country_unique": "Canada;United Kingdom" }, { "id": "85781bfa79", "title": "Recognizing Hand-written Digits Using Hierarchical Products of Experts", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/1f1baa5b8edac74eb4eaa329f14a0361-Abstract.html", "author": "Guy Mayraz; Geoffrey E. Hinton", "abstract": "The product of experts learning procedure [1] can discover a set of stochastic binary features that constitute a non-linear generative model of handwritten images of digits. The quality of generative models learned in this way can be assessed by learning a separate model for each class of digit and then comparing the unnormalized probabilities of test images under the 10 different class-specific models. To improve discriminative performance, it is helpful to learn a hierarchy of separate models for each digit class. Each model in the hierarchy has one layer of hidden units and the nth level model is trained on data that consists of the activities of the hidden units in the already trained (n - l)th level model. After train(cid:173) ing, each level produces a separate, unnormalized log probabilty score. With a three-level hierarchy for each of the 10 digit classes, a test image produces 30 scores which can be used as inputs to a supervised, logis(cid:173) tic classification network that is trained on separate data. On the MNIST database, our system is comparable with current state-of-the-art discrimi(cid:173) native methods, demonstrating that the product of experts learning proce(cid:173) dure can produce effective generative models of high-dimensional data.", "bibtex": "@inproceedings{NIPS2000_1f1baa5b,\n author = {Mayraz, Guy and Hinton, Geoffrey E},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Recognizing Hand-written Digits Using Hierarchical Products of Experts},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/1f1baa5b8edac74eb4eaa329f14a0361-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/1f1baa5b8edac74eb4eaa329f14a0361-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/1f1baa5b8edac74eb4eaa329f14a0361-Metadata.json", "review": "", "metareview": "", "pdf_size": 1400197, "gs_citation": 113, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=9272264145884360664&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 25, "aff": ";", "aff_domain": ";", "email": ";", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster" }, { "id": "82a18aca39", "title": "Redundancy and Dimensionality Reduction in Sparse-Distributed Representations of Natural Objects in Terms of Their Local Features", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/052335232b11864986bb2fa20fa38748-Abstract.html", "author": "Penio S. Penev", "abstract": "Low-dimensional representations are key to solving problems in high(cid:173) level vision, such as face compression and recognition. Factorial coding strategies for reducing the redundancy present in natural images on the basis of their second-order statistics have been successful in account(cid:173) ing for both psychophysical and neurophysiological properties of early vision. Class-specific representations are presumably formed later, at the higher-level stages of cortical processing. Here we show that when retinotopic factorial codes are derived for ensembles of natural objects, such as human faces, not only redundancy, but also dimensionality is re(cid:173) duced. We also show that objects are built from parts in a non-Gaussian fashion which allows these local-feature codes to have dimensionalities that are substantially lower than the respective Nyquist sampling rates.", "bibtex": "@inproceedings{NIPS2000_05233523,\n author = {Penev, Penio},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Redundancy and Dimensionality Reduction in Sparse-Distributed Representations of Natural Objects in Terms of Their Local Features},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/052335232b11864986bb2fa20fa38748-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/052335232b11864986bb2fa20fa38748-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/052335232b11864986bb2fa20fa38748-Metadata.json", "review": "", "metareview": "", "pdf_size": 1394163, "gs_citation": 10, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=539167548631250900&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 7, "aff": "", "aff_domain": "", "email": "", "github": "", "project": "http://venezia.rockefeller.edu/", "author_num": 1, "track": "main", "status": "Poster" }, { "id": "189efe2604", "title": "Regularization with Dot-Product Kernels", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/d25414405eb37dae1c14b18d6a2cac34-Abstract.html", "author": "Alex J. Smola; Zolt\u00e1n L. \u00d3v\u00e1ri; Robert C. Williamson", "abstract": "In this paper we give necessary and sufficient conditions under which kernels of dot product type k(x, y) = k(x . y) satisfy Mer(cid:173) cer's condition and thus may be used in Support Vector Ma(cid:173) chines (SVM), Regularization Networks (RN) or Gaussian Pro(cid:173) cesses (GP). In particular, we show that if the kernel is analytic (i.e. can be expanded in a Taylor series), all expansion coefficients have to be nonnegative. We give an explicit functional form for the feature map by calculating its eigenfunctions and eigenvalues.", "bibtex": "@inproceedings{NIPS2000_d2541440,\n author = {Smola, Alex and \\'{O}v\\'{a}ri, Zolt\\'{a}n and Williamson, Robert C},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Regularization with Dot-Product Kernels},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/d25414405eb37dae1c14b18d6a2cac34-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/d25414405eb37dae1c14b18d6a2cac34-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/d25414405eb37dae1c14b18d6a2cac34-Metadata.json", "review": "", "metareview": "", "pdf_size": 1279078, "gs_citation": 140, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=13730258226103020943&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 9, "aff": ";;", "aff_domain": ";;", "email": ";;", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster" }, { "id": "dd211193cc", "title": "Regularized Winnow Methods", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/9a1de01f893e0d2551ecbb7ce4dc963e-Abstract.html", "author": "Tong Zhang", "abstract": "In theory, the Winnow multiplicative update has certain advantages over the Perceptron additive update when there are many irrelevant attributes. Recently, there has been much effort on enhancing the Perceptron algo(cid:173) rithm by using regularization, leading to a class of linear classification methods called support vector machines. Similarly, it is also possible to apply the regularization idea to the Winnow algorithm, which gives meth(cid:173) ods we call regularized Winnows. We show that the resulting methods compare with the basic Winnows in a similar way that a support vector machine compares with the Perceptron. We investigate algorithmic is(cid:173) sues and learning properties of the derived methods. Some experimental results will also be provided to illustrate different methods.", "bibtex": "@inproceedings{NIPS2000_9a1de01f,\n author = {Zhang, Tong},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Regularized Winnow Methods},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/9a1de01f893e0d2551ecbb7ce4dc963e-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/9a1de01f893e0d2551ecbb7ce4dc963e-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/9a1de01f893e0d2551ecbb7ce4dc963e-Metadata.json", "review": "", "metareview": "", "pdf_size": 1431614, "gs_citation": 53, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=8041359600669284778&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 15, "aff": "Mathematical Sciences Department, IBM TJ. Watson Research Center", "aff_domain": "watson.ibm.com", "email": "watson.ibm.com", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "IBM", "aff_unique_dep": "Mathematical Sciences Department", "aff_unique_url": "https://www.ibm.com/research/watson", "aff_unique_abbr": "IBM Watson", "aff_country_unique_index": "0", "aff_country_unique": "United States" }, { "id": "3fbdf3733f", "title": "Reinforcement Learning with Function Approximation Converges to a Region", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/04df4d434d481c5bb723be1b6df1ee65-Abstract.html", "author": "Geoffrey J. Gordon", "abstract": "Many algorithms for approximate reinforcement learning are not known to converge. In fact, there are counterexamples showing that the adjustable weights in some algorithms may oscillate within a region rather than converging to a point. This paper shows that, for two popular algorithms, such oscillation is the worst that can happen: the weights cannot diverge, but instead must converge to a bounded region. The algorithms are SARSA(O) and V(O); the latter algorithm was used in the well-known TD-Gammon program.", "bibtex": "@inproceedings{NIPS2000_04df4d43,\n author = {Gordon, Geoffrey J},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Reinforcement Learning with Function Approximation Converges to a Region},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/04df4d434d481c5bb723be1b6df1ee65-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/04df4d434d481c5bb723be1b6df1ee65-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/04df4d434d481c5bb723be1b6df1ee65-Metadata.json", "review": "", "metareview": "", "pdf_size": 1469167, "gs_citation": 195, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=8842088888932940252&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 6, "aff": "", "aff_domain": "es.emu.edu", "email": "es.emu.edu", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster" }, { "id": "7a1c0232e2", "title": "Robust Reinforcement Learning", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/e8dfff4676a47048d6f0c4ef899593dd-Abstract.html", "author": "Jun Morimoto; Kenji Doya", "abstract": "This paper proposes a new reinforcement learning (RL) paradigm that explicitly takes into account input disturbance as well as mod(cid:173) eling errors. The use of environmental models in RL is quite pop(cid:173) ular for both off-line learning by simulations and for on-line ac(cid:173) tion planning. However, the difference between the model and the real environment can lead to unpredictable, often unwanted results. Based on the theory of H oocontrol, we consider a differential game in which a 'disturbing' agent (disturber) tries to make the worst possible disturbance while a 'control' agent (actor) tries to make the best control input. The problem is formulated as finding a min(cid:173) max solution of a value function that takes into account the norm of the output deviation and the norm of the disturbance. We derive on-line learning algorithms for estimating the value function and for calculating the worst disturbance and the best control in refer(cid:173) ence to the value function. We tested the paradigm, which we call \"Robust Reinforcement Learning (RRL),\" in the task of inverted pendulum. In the linear domain, the policy and the value func(cid:173) tion learned by the on-line algorithms coincided with those derived analytically by the linear H ootheory. For a fully nonlinear swing(cid:173) up task, the control by RRL achieved robust performance against changes in the pendulum weight and friction while a standard RL control could not deal with such environmental changes.", "bibtex": "@inproceedings{NIPS2000_e8dfff46,\n author = {Morimoto, Jun and Doya, Kenji},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Robust Reinforcement Learning},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/e8dfff4676a47048d6f0c4ef899593dd-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/e8dfff4676a47048d6f0c4ef899593dd-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/e8dfff4676a47048d6f0c4ef899593dd-Metadata.json", "review": "", "metareview": "", "pdf_size": 1082762, "gs_citation": 336, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=13676841137999016830&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 10, "aff": "Graduate School of Information Science, Nara Institute of Science and Technology + Kawato Dynamic Brain Project, JST; ATR International + CREST, JST", "aff_domain": "erato.atr.co.jp;isd.atr.co.jp", "email": "erato.atr.co.jp;isd.atr.co.jp", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0+1;2+3", "aff_unique_norm": "Nara Institute of Science and Technology;Japan Science and Technology Agency;ATR International;CREST", "aff_unique_dep": "Graduate School of Information Science;Kawato Dynamic Brain Project;;", "aff_unique_url": "https://www.nist.go.jp;https://www.jst.go.jp;https://www.atr-intl.jp;https://www.jst.go.jp/crest/en/", "aff_unique_abbr": "NIST;JST;;CREST", "aff_campus_unique_index": "0;", "aff_campus_unique": "Nara;", "aff_country_unique_index": "0+0;0+0", "aff_country_unique": "Japan" }, { "id": "3e0f4a0892", "title": "Second Order Approximations for Probability Models", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/865dfbde8a344b44095495f3591f7407-Abstract.html", "author": "Hilbert J. Kappen; Wim Wiegerinck", "abstract": "In this paper, we derive a second order mean field theory for directed graphical probability models. By using an information theoretic argu(cid:173) ment it is shown how this can be done in the absense of a partition function. This method is a direct generalisation of the well-known TAP approximation for Boltzmann Machines. In a numerical example, it is shown that the method greatly improves the first order mean field ap(cid:173) proximation. For a restricted class of graphical models, so-called single overlap graphs, the second order method has comparable complexity to the first order method. For sigmoid belief networks, the method is shown to be particularly fast and effective.", "bibtex": "@inproceedings{NIPS2000_865dfbde,\n author = {Kappen, Hilbert and Wiegerinck, Wim},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Second Order Approximations for Probability Models},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/865dfbde8a344b44095495f3591f7407-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/865dfbde8a344b44095495f3591f7407-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/865dfbde8a344b44095495f3591f7407-Metadata.json", "review": "", "metareview": "", "pdf_size": 1078934, "gs_citation": 15, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=12110600762304437863&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 11, "aff": "Department of Biophysics, Nijmegen University, Nijmegen, the Netherlands; Department of Biophysics, Nijmegen University, Nijmegen, the Netherlands", "aff_domain": "mbfys.kun.nl;mbfys.kun.nl", "email": "mbfys.kun.nl;mbfys.kun.nl", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Nijmegen University", "aff_unique_dep": "Department of Biophysics", "aff_unique_url": "https://www.ru.nl/", "aff_unique_abbr": "", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Nijmegen", "aff_country_unique_index": "0;0", "aff_country_unique": "Netherlands" }, { "id": "3c7b3a5dd3", "title": "Sequentially Fitting ``Inclusive'' Trees for Inference in Noisy-OR Networks", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f0bbac6fa079f1e00b2c14c1d3c6ccf0-Abstract.html", "author": "Brendan J. Frey; Relu Patrascu; Tommi Jaakkola; Jodi Moran", "abstract": "An important class of problems can be cast as inference in noisy(cid:173) OR Bayesian networks, where the binary state of each variable is a logical OR of noisy versions of the states of the variable's par(cid:173) ents. For example, in medical diagnosis, the presence of a symptom can be expressed as a noisy-OR of the diseases that may cause the symptom - on some occasions, a disease may fail to activate the symptom. Inference in richly-connected noisy-OR networks is in(cid:173) tractable, but approximate methods (e .g., variational techniques) are showing increasing promise as practical solutions. One prob(cid:173) lem with most approximations is that they tend to concentrate on a relatively small number of modes in the true posterior, ig(cid:173) noring other plausible configurations of the hidden variables. We introduce a new sequential variational method for bipartite noisy(cid:173) OR networks, that favors including all modes of the true posterior and models the posterior distribution as a tree. We compare this method with other approximations using an ensemble of networks with network statistics that are comparable to the QMR-DT med(cid:173) ical diagnostic network.", "bibtex": "@inproceedings{NIPS2000_f0bbac6f,\n author = {Frey, Brendan J and Patrascu, Relu and Jaakkola, Tommi and Moran, Jodi},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Sequentially Fitting \\textasciigrave \\textasciigrave Inclusive\\textquotesingle \\textquotesingle Trees for Inference in Noisy-OR Networks},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f0bbac6fa079f1e00b2c14c1d3c6ccf0-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f0bbac6fa079f1e00b2c14c1d3c6ccf0-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f0bbac6fa079f1e00b2c14c1d3c6ccf0-Metadata.json", "review": "", "metareview": "", "pdf_size": 1267392, "gs_citation": 40, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=3356718677633583939&as_sdt=400005&sciodt=0,14&hl=en", "gs_version_total": 4, "aff": "Intelligent Algorithms Lab, University of Toronto; Computer Science and Electrical Engineering, Massachusetts Institute of Technology; Intelligent Algorithms Lab, University of Toronto; Computer Science and Electrical Engineering, Massachusetts Institute of Technology", "aff_domain": "cs.toronto.edu;mit.edu;cs.toronto.edu;mit.edu", "email": "cs.toronto.edu;mit.edu;cs.toronto.edu;mit.edu", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster", "aff_unique_index": "0;1;0;1", "aff_unique_norm": "University of Toronto;Massachusetts Institute of Technology", "aff_unique_dep": "Intelligent Algorithms Lab;Computer Science and Electrical Engineering", "aff_unique_url": "https://www.utoronto.ca;https://web.mit.edu", "aff_unique_abbr": "U of T;MIT", "aff_campus_unique_index": "0;1;0;1", "aff_campus_unique": "Toronto;Cambridge", "aff_country_unique_index": "0;1;0;1", "aff_country_unique": "Canada;United States" }, { "id": "f36fa36439", "title": "Sex with Support Vector Machines", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/1e913e1b06ead0b66e30b6867bf63549-Abstract.html", "author": "Baback Moghaddam; Ming-Hsuan Yang", "abstract": "Nonlinear Support Vector Machines (SVMs) are investigated for visual sex classification with low resolution \"thumbnail\" faces (21- by-12 pixels) processed from 1,755 images from the FE RET face database. The performance of SVMs is shown to be superior to traditional pattern classifiers (Linear, Quadratic, Fisher Linear Dis(cid:173) criminant, Nearest-Neighbor) as well as more modern techniques such as Radial Basis Function (RBF) classifiers and large ensemble(cid:173) RBF networks. Furthermore, the SVM performance (3.4% error) is currently the best result reported in the open literature.", "bibtex": "@inproceedings{NIPS2000_1e913e1b,\n author = {Moghaddam, Baback and Yang, Ming-Hsuan},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Sex with Support Vector Machines},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/1e913e1b06ead0b66e30b6867bf63549-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/1e913e1b06ead0b66e30b6867bf63549-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/1e913e1b06ead0b66e30b6867bf63549-Metadata.json", "review": "", "metareview": "", "pdf_size": 1232555, "gs_citation": 28, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=12858522823893533187&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 12, "aff": "Mitsubishi Electric Research Laboratory, Cambridge MA 02139, USA; University of Illinois at Urbana-Champaign, Urbana, IL 61801 USA", "aff_domain": "amerl.com;avision.ai.uiuc.edu", "email": "amerl.com;avision.ai.uiuc.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Mitsubishi Electric Research Laboratory;University of Illinois Urbana-Champaign", "aff_unique_dep": ";", "aff_unique_url": "https://www.merl.com;https://illinois.edu", "aff_unique_abbr": "MERL;UIUC", "aff_campus_unique_index": "0;1", "aff_campus_unique": "Cambridge;Urbana", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "15aa58a275", "title": "Shape Context: A New Descriptor for Shape Matching and Object Recognition", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/c44799b04a1c72e3c8593a53e8000c78-Abstract.html", "author": "Serge Belongie; Jitendra Malik; Jan Puzicha", "abstract": "We develop an approach to object recognition based on match(cid:173) ing shapes and using a resulting measure of similarity in a nearest neighbor classifier. The key algorithmic problem here is that of finding pointwise correspondences between an image shape and a stored prototype shape. We introduce a new shape descriptor, the shape context, which makes this possible, using a simple and robust algorithm. The shape context at a point captures the distri(cid:173) bution over relative positions of other shape points and thus sum(cid:173) marizes global shape in a rich, local descriptor. We demonstrate that shape contexts greatly simplify recovery of correspondences between points of two given shapes. Once shapes are aligned, shape contexts are used to define a robust score for measuring shape sim(cid:173) ilarity. We have used this score in a nearest-neighbor classifier for recognition of hand written digits as well as 3D objects, using exactly the same distance function. On the benchmark MNIST dataset of handwritten digits, this yields an error rate of 0.63%, outperforming other published techniques.", "bibtex": "@inproceedings{NIPS2000_c44799b0,\n author = {Belongie, Serge and Malik, Jitendra and Puzicha, Jan},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Shape Context: A New Descriptor for Shape Matching and Object Recognition},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/c44799b04a1c72e3c8593a53e8000c78-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/c44799b04a1c72e3c8593a53e8000c78-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/c44799b04a1c72e3c8593a53e8000c78-Metadata.json", "review": "", "metareview": "", "pdf_size": 1426269, "gs_citation": 877, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11312321152795732384&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 9, "aff": ";;", "aff_domain": ";;", "email": ";;", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster" }, { "id": "487b8909af", "title": "Smart Vision Chip Fabricated Using Three Dimensional Integration Technology", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/ff7d0f525b3be596a51fb919492c099c-Abstract.html", "author": "Hiroyuki Kurino; M. Nakagawa; Kang Wook Lee; Tomonori Nakamura; Yuusuke Yamada; Ki Tae Park; Mitsumasa Koyanagi", "abstract": "The smart VISIOn chip has a large potential for application in general purpose high speed image processing systems. In order to fabricate smart vision chips including photo detector compactly, we have proposed the application of three dimensional LSI technology for smart vision chips. Three dimensional technology has great potential to realize new neuromorphic systems inspired by not only the biological function but also the biological structure. In this paper, we describe our three dimensional LSI technology for neuromorphic circuits and the design of smart vision chips .", "bibtex": "@inproceedings{NIPS2000_ff7d0f52,\n author = {Kurino, Hiroyuki and Nakagawa, M. and Lee, Kang and Nakamura, Tomonori and Yamada, Yuusuke and Park, Ki and Koyanagi, Mitsumasa},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Smart Vision Chip Fabricated Using Three Dimensional Integration Technology},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/ff7d0f525b3be596a51fb919492c099c-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/ff7d0f525b3be596a51fb919492c099c-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/ff7d0f525b3be596a51fb919492c099c-Metadata.json", "review": "", "metareview": "", "pdf_size": 463665, "gs_citation": 21, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=13013962935898564620&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 7, "aff": "Dept. of Machine Intelligence and Systems Engineering, Tohoku University; Dept. of Machine Intelligence and Systems Engineering, Tohoku University; Dept. of Machine Intelligence and Systems Engineering, Tohoku University; Dept. of Machine Intelligence and Systems Engineering, Tohoku University; Dept. of Machine Intelligence and Systems Engineering, Tohoku University; Dept. of Machine Intelligence and Systems Engineering, Tohoku University; Dept. of Machine Intelligence and Systems Engineering, Tohoku University", "aff_domain": "sd.mech.tohoku.ac.jp; ; ; ; ; ; ", "email": "sd.mech.tohoku.ac.jp; ; ; ; ; ; ", "github": "", "project": "", "author_num": 7, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0;0;0;0;0", "aff_unique_norm": "Tohoku University", "aff_unique_dep": "Dept. of Machine Intelligence and Systems Engineering", "aff_unique_url": "https://www.tohoku.ac.jp", "aff_unique_abbr": "Tohoku U", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0;0;0;0;0;0", "aff_country_unique": "Japan" }, { "id": "28789553c1", "title": "Some New Bounds on the Generalization Error of Combined Classifiers", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/6be5336db2c119736cf48f475e051bfe-Abstract.html", "author": "Vladimir Koltchinskii; Dmitriy Panchenko; Fernando Lozano", "abstract": "In this paper we develop the method of bounding the generalization error of a classifier in terms of its margin distribution which was introduced in the recent papers of Bartlett and Schapire, Freund, Bartlett and Lee. The theory of Gaussian and empirical processes allow us to prove the margin type inequalities for the most general functional classes, the complexity of the class being measured via the so called Gaussian complexity func(cid:173) tions. As a simple application of our results, we obtain the bounds of Schapire, Freund, Bartlett and Lee for the generalization error of boost(cid:173) ing. We also substantially improve the results of Bartlett on bounding the generalization error of neural networks in terms of h -norms of the weights of neurons. Furthermore, under additional assumptions on the complexity of the class of hypotheses we provide some tighter bounds, which in the case of boosting improve the results of Schapire, Freund, Bartlett and Lee.", "bibtex": "@inproceedings{NIPS2000_6be5336d,\n author = {Koltchinskii, Vladimir and Panchenko, Dmitriy and Lozano, Fernando},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Some New Bounds on the Generalization Error of Combined Classifiers},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/6be5336db2c119736cf48f475e051bfe-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/6be5336db2c119736cf48f475e051bfe-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/6be5336db2c119736cf48f475e051bfe-Metadata.json", "review": "", "metareview": "", "pdf_size": 1077654, "gs_citation": 34, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=15003027955704089768&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 8, "aff": "Department of Mathematics and Statistics, University of New Mexico; Department of Mathematics and Statistics, University of New Mexico; Department of Electrical and Computer Engineering, University of New Mexico", "aff_domain": "math.unm.edu;math.unm.edu;eece.unm.edu", "email": "math.unm.edu;math.unm.edu;eece.unm.edu", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0", "aff_unique_norm": "University of New Mexico", "aff_unique_dep": "Department of Mathematics and Statistics", "aff_unique_url": "https://www.unm.edu", "aff_unique_abbr": "UNM", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "4bbd9f18cd", "title": "Sparse Greedy Gaussian Process Regression", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/3214a6d842cc69597f9edf26df552e43-Abstract.html", "author": "Alex J. Smola; Peter L. Bartlett", "abstract": "We present a simple sparse greedy technique to approximate the maximum a posteriori estimate of Gaussian Processes with much improved scaling behaviour in the sample size m. In particular, computational requirements are O(n2m), storage is O(nm), the cost for prediction is 0 ( n) and the cost to compute confidence bounds is O(nm), where n \u00ab: m. We show how to compute a stopping criterion, give bounds on the approximation error, and show applications to large scale problems.", "bibtex": "@inproceedings{NIPS2000_3214a6d8,\n author = {Smola, Alex and Bartlett, Peter},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Sparse Greedy Gaussian Process Regression},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/3214a6d842cc69597f9edf26df552e43-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/3214a6d842cc69597f9edf26df552e43-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/3214a6d842cc69597f9edf26df552e43-Metadata.json", "review": "", "metareview": "", "pdf_size": 1442396, "gs_citation": 560, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=7894130899184005903&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 9, "aff": "RSISE and Department of Engineering, Australian National University; RSISE, Australian National University", "aff_domain": "anu.edu.au;anu.edu.au", "email": "anu.edu.au;anu.edu.au", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Australian National University", "aff_unique_dep": "Department of Engineering", "aff_unique_url": "https://www.anu.edu.au", "aff_unique_abbr": "ANU", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "Australia" }, { "id": "2658dc3b3d", "title": "Sparse Kernel Principal Component Analysis", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/bf201d5407a6509fa536afc4b380577e-Abstract.html", "author": "Michael E. Tipping", "abstract": "'Kernel' principal component analysis (PCA) is an elegant non(cid:173) linear generalisation of the popular linear data analysis method, where a kernel function implicitly defines a nonlinear transforma(cid:173) tion into a feature space wherein standard PCA is performed. Un(cid:173) fortunately, the technique is not 'sparse', since the components thus obtained are expressed in terms of kernels associated with ev(cid:173) ery training vector. This paper shows that by approximating the covariance matrix in feature space by a reduced number of exam(cid:173) ple vectors, using a maximum-likelihood approach, we may obtain a highly sparse form of kernel PCA without loss of effectiveness.", "bibtex": "@inproceedings{NIPS2000_bf201d54,\n author = {Tipping, Michael},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Sparse Kernel Principal Component Analysis},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/bf201d5407a6509fa536afc4b380577e-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/bf201d5407a6509fa536afc4b380577e-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/bf201d5407a6509fa536afc4b380577e-Metadata.json", "review": "", "metareview": "", "pdf_size": 1150291, "gs_citation": 234, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=9907321444464369052&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 6, "aff": "Microsoft Research", "aff_domain": "microsoft.com", "email": "microsoft.com", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "Microsoft", "aff_unique_dep": "Microsoft Research", "aff_unique_url": "https://www.microsoft.com/en-us/research", "aff_unique_abbr": "MSR", "aff_country_unique_index": "0", "aff_country_unique": "United States" }, { "id": "02d47affea", "title": "Sparse Representation for Gaussian Process Models", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/56f9f88906aebf4ad985aaec7fa01313-Abstract.html", "author": "Lehel Csat\u00f3; Manfred Opper", "abstract": "We develop an approach for a sparse representation for Gaussian Process (GP) models in order to overcome the limitations of GPs caused by large data sets. The method is based on a combination of a Bayesian online al(cid:173) gorithm together with a sequential construction of a relevant subsample of the data which fully specifies the prediction of the model. Experi(cid:173) mental results on toy examples and large real-world data sets indicate the efficiency of the approach.", "bibtex": "@inproceedings{NIPS2000_56f9f889,\n author = {Csat\\'{o}, Lehel and Opper, Manfred},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Sparse Representation for Gaussian Process Models},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/56f9f88906aebf4ad985aaec7fa01313-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/56f9f88906aebf4ad985aaec7fa01313-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/56f9f88906aebf4ad985aaec7fa01313-Metadata.json", "review": "", "metareview": "", "pdf_size": 1261458, "gs_citation": 184, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=1945091839318607865&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 14, "aff": "Neural Computing Research Group, School of Engineering and Applied Sciences, B4 7ET Birmingham, United Kingdom; Neural Computing Research Group, School of Engineering and Applied Sciences, B4 7ET Birmingham, United Kingdom", "aff_domain": "aston.ac.uk;aston.ac.uk", "email": "aston.ac.uk;aston.ac.uk", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "University of Birmingham", "aff_unique_dep": "School of Engineering and Applied Sciences", "aff_unique_url": "https://www.birmingham.ac.uk", "aff_unique_abbr": "UoB", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Birmingham", "aff_country_unique_index": "0;0", "aff_country_unique": "United Kingdom" }, { "id": "6a98ad7870", "title": "Sparsity of Data Representation of Optimal Kernel Machine and Leave-one-out Estimator", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/c164bbc9d6c72a52c599bbb43d8db8e1-Abstract.html", "author": "Adam Kowalczyk", "abstract": "Vapnik's result that the expectation of the generalisation error ofthe opti(cid:173) mal hyperplane is bounded by the expectation of the ratio of the number of support vectors to the number of training examples is extended to a broad class of kernel machines. The class includes Support Vector Ma(cid:173) chines for soft margin classification and regression, and Regularization Networks with a variety of kernels and cost functions. We show that key inequalities in Vapnik's result become equalities once \"the classification error\" is replaced by \"the margin error\", with the latter defined as an in(cid:173) stance with positive cost. In particular we show that expectations of the true margin error and the empirical margin error are equal, and that the sparse solutions for kernel machines are possible only if the cost function is \"partially\" insensitive.", "bibtex": "@inproceedings{NIPS2000_c164bbc9,\n author = {Kowalczyk, Adam},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Sparsity of Data Representation of Optimal Kernel Machine and Leave-one-out Estimator},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/c164bbc9d6c72a52c599bbb43d8db8e1-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/c164bbc9d6c72a52c599bbb43d8db8e1-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/c164bbc9d6c72a52c599bbb43d8db8e1-Metadata.json", "review": "", "metareview": "", "pdf_size": 1225615, "gs_citation": 4, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=468825624110176119&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 10, "aff": "Chief Technology Office, Telstra", "aff_domain": "team.telstra.com", "email": "team.telstra.com", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "Telstra", "aff_unique_dep": "Chief Technology Office", "aff_unique_url": "https://www.telstra.com.au", "aff_unique_abbr": "Telstra", "aff_country_unique_index": "0", "aff_country_unique": "Australia" }, { "id": "43de473a40", "title": "Speech Denoising and Dereverberation Using Probabilistic Models", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/65699726a3c601b9f31bf04019c8593c-Abstract.html", "author": "Hagai Attias; John C. Platt; Alex Acero; Li Deng", "abstract": "This paper presents a unified probabilistic framework for denoising and dereverberation of speech signals. The framework transforms the denois(cid:173) ing and dereverberation problems into Bayes-optimal signal estimation. The key idea is to use a strong speech model that is pre-trained on a large data set of clean speech. Computational efficiency is achieved by using variational EM, working in the frequency domain, and employing conjugate priors. The framework covers both single and multiple micro(cid:173) phones. We apply this approach to noisy reverberant speech signals and get results substantially better than standard methods.", "bibtex": "@inproceedings{NIPS2000_65699726,\n author = {Attias, Hagai and Platt, John and Acero, Alex and Deng, Li},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Speech Denoising and Dereverberation Using Probabilistic Models},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/65699726a3c601b9f31bf04019c8593c-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/65699726a3c601b9f31bf04019c8593c-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/65699726a3c601b9f31bf04019c8593c-Metadata.json", "review": "", "metareview": "", "pdf_size": 1439698, "gs_citation": 147, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=3304133367853599315&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 10, "aff": "Microsoft Research; Microsoft Research; Microsoft Research; Microsoft Research", "aff_domain": "microsoft.com;microsoft.com;microsoft.com;microsoft.com", "email": "microsoft.com;microsoft.com;microsoft.com;microsoft.com", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0;0", "aff_unique_norm": "Microsoft", "aff_unique_dep": "Microsoft Research", "aff_unique_url": "https://www.microsoft.com/en-us/research", "aff_unique_abbr": "MSR", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0;0;0", "aff_country_unique": "United States" }, { "id": "6d0029075f", "title": "Spike-Timing-Dependent Learning for Oscillatory Networks", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/4496bf24afe7fab6f046bf4923da8de6-Abstract.html", "author": "Silvia Scarpetta; Zhaoping Li; John A. Hertz", "abstract": "We apply to oscillatory networks a class of learning rules in which synaptic weights change proportional to pre- and post-synaptic ac(cid:173) tivity, with a kernel A(r) measuring the effect for a postsynaptic spike a time r after the presynaptic one. The resulting synaptic ma(cid:173) trices have an outer-product form in which the oscillating patterns are represented as complex vectors. In a simple model, the even part of A(r) enhances the resonant response to learned stimulus by reducing the effective damping, while the odd part determines the frequency of oscillation. We relate our model to the olfactory cortex and hippocampus and their presumed roles in forming associative memories and input representations.", "bibtex": "@inproceedings{NIPS2000_4496bf24,\n author = {Scarpetta, Silvia and Li, Zhaoping and Hertz, John},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Spike-Timing-Dependent Learning for Oscillatory Networks},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/4496bf24afe7fab6f046bf4923da8de6-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/4496bf24afe7fab6f046bf4923da8de6-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/4496bf24afe7fab6f046bf4923da8de6-Metadata.json", "review": "", "metareview": "", "pdf_size": 1332489, "gs_citation": 8, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=228996062665341132&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 7, "aff": "Dept. of Physics 'E.R. Caianiello', Salerno University 84081 (SA) Italy + INFM, Sezione di Salerno Italy; Gatsby Compo Neurosci. Unit, University College, London, WCIN 3AR United Kingdom; Nordita, 2100 Copenhagen 0, Denmark", "aff_domain": "na.infn.it;gatsby.ucl.ac.uk;nordita.dk", "email": "na.infn.it;gatsby.ucl.ac.uk;nordita.dk", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0+1;2;3", "aff_unique_norm": "Salerno University;Istituto Nazionale di Fisica della Materia;University College London;Nordita", "aff_unique_dep": "Dept. of Physics 'E.R. Caianiello';;Gatsby Computational Neuroscience Unit;", "aff_unique_url": ";;https://www.ucl.ac.uk;https://www.nordita.org", "aff_unique_abbr": ";INFM;UCL;", "aff_campus_unique_index": "1;2;3", "aff_campus_unique": ";Salerno;London;Copenhagen", "aff_country_unique_index": "0+0;1;2", "aff_country_unique": "Italy;United Kingdom;Denmark" }, { "id": "999c36c090", "title": "Stability and Noise in Biochemical Switches", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/82cadb0649a3af4968404c9f6031b233-Abstract.html", "author": "William Bialek", "abstract": "Many processes in biology, from the regulation of gene expression in bacteria to memory in the brain, involve switches constructed from networks of biochemical reactions. Crucial molecules are present in small numbers, raising questions about noise and stability. Analysis of noise in simple reaction schemes indicates that switches stable for years and switchable in milliseconds can be built from fewer than one hundred molecules. Prospects for direct tests of this prediction, as well as implications, are discussed.", "bibtex": "@inproceedings{NIPS2000_82cadb06,\n author = {Bialek, William},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Stability and Noise in Biochemical Switches},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/82cadb0649a3af4968404c9f6031b233-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/82cadb0649a3af4968404c9f6031b233-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/82cadb0649a3af4968404c9f6031b233-Metadata.json", "review": "", "metareview": "", "pdf_size": 1449151, "gs_citation": 95, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=2634426078399464320&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 21, "aff": "NEC Research Institute", "aff_domain": "research.nj.nec.com", "email": "research.nj.nec.com", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "NEC Research Institute", "aff_unique_dep": "", "aff_unique_url": "https://www.neclab.eu", "aff_unique_abbr": "NEC RI", "aff_country_unique_index": "0", "aff_country_unique": "United States" }, { "id": "a9cdaf0a66", "title": "Stagewise Processing in Error-correcting Codes and Image Restoration", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/d7fd118e6f226a71b5f1ffe10efd0a78-Abstract.html", "author": "K. Y. Michael Wong; Hidetoshi Nishimori", "abstract": "We introduce stagewise processing in error-correcting codes and image restoration, by extracting information from the former stage and using it selectively to improve the performance of the latter one. Both mean-field analysis using the cavity method and sim(cid:173) ulations show that it has the advantage of being robust against uncertainties in hyperparameter estimation.", "bibtex": "@inproceedings{NIPS2000_d7fd118e,\n author = {Wong, K. Y. Michael and Nishimori, Hidetoshi},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Stagewise Processing in Error-correcting Codes and Image Restoration},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/d7fd118e6f226a71b5f1ffe10efd0a78-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/d7fd118e6f226a71b5f1ffe10efd0a78-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/d7fd118e6f226a71b5f1ffe10efd0a78-Metadata.json", "review": "", "metareview": "", "pdf_size": 1280752, "gs_citation": 0, "gs_cited_by_link": "https://scholar.google.com/scholar?q=related:MJbD5yuNtvkJ:scholar.google.com/&scioq=Stagewise+Processing+in+Error-correcting+Codes+and+Image+Restoration&hl=en&as_sdt=0,33", "gs_version_total": 6, "aff": "Department of Physics, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong; Department of Physics, Tokyo Institute of Technology, Oh-Okayama, Meguro-ku, Tokyo 152-8551, Japan", "aff_domain": "ust.hk;stat.phys.titech.ac.jp", "email": "ust.hk;stat.phys.titech.ac.jp", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Hong Kong University of Science and Technology;Tokyo Institute of Technology", "aff_unique_dep": "Department of Physics;Department of Physics", "aff_unique_url": "https://www.ust.hk;https://www.titech.ac.jp", "aff_unique_abbr": "HKUST;Titech", "aff_campus_unique_index": "0;1", "aff_campus_unique": "Hong Kong SAR;Oh-Okayama", "aff_country_unique_index": "0;1", "aff_country_unique": "China;Japan" }, { "id": "c3dbd3f7d5", "title": "Structure Learning in Human Causal Induction", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/59bcda7c438bad7d2afffe9e2fed00be-Abstract.html", "author": "Joshua B. Tenenbaum; Thomas L. Griffiths", "abstract": "We use graphical models to explore the question of how people learn sim(cid:173) ple causal relationships from data. The two leading psychological theo(cid:173) ries can both be seen as estimating the parameters of a fixed graph. We argue that a complete account of causal induction should also consider how people learn the underlying causal graph structure, and we propose to model this inductive process as a Bayesian inference. Our argument is supported through the discussion of three data sets.", "bibtex": "@inproceedings{NIPS2000_59bcda7c,\n author = {Tenenbaum, Joshua and Griffiths, Thomas},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Structure Learning in Human Causal Induction},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/59bcda7c438bad7d2afffe9e2fed00be-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/59bcda7c438bad7d2afffe9e2fed00be-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/59bcda7c438bad7d2afffe9e2fed00be-Metadata.json", "review": "", "metareview": "", "pdf_size": 1408859, "gs_citation": 197, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=7790477364891864857&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 15, "aff": "Department of Psychology, Stanford University, Stanford, CA 94305; Department of Psychology, Stanford University, Stanford, CA 94305", "aff_domain": "psych.stanford.edu;psych.stanford.edu", "email": "psych.stanford.edu;psych.stanford.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Stanford University", "aff_unique_dep": "Department of Psychology", "aff_unique_url": "https://www.stanford.edu", "aff_unique_abbr": "Stanford", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Stanford", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "29049a6e3b", "title": "Support Vector Novelty Detection Applied to Jet Engine Vibration Spectra", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/7302e3f5e7c072aea8801faf8a492be0-Abstract.html", "author": "Paul M. Hayton; Bernhard Sch\u00f6lkopf; Lionel Tarassenko; Paul Anuzis", "abstract": "A system has been developed to extract diagnostic information from jet engine carcass vibration data. Support Vector Machines applied to nov(cid:173) elty detection provide a measure of how unusual the shape of a vibra(cid:173) tion signature is, by learning a representation of normality. We describe a novel method for Support Vector Machines of including information from a second class for novelty detection and give results from the appli(cid:173) cation to Jet Engine vibration analysis.", "bibtex": "@inproceedings{NIPS2000_7302e3f5,\n author = {Hayton, Paul and Sch\\\"{o}lkopf, Bernhard and Tarassenko, Lionel and Anuzis, Paul},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Support Vector Novelty Detection Applied to Jet Engine Vibration Spectra},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/7302e3f5e7c072aea8801faf8a492be0-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/7302e3f5e7c072aea8801faf8a492be0-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/7302e3f5e7c072aea8801faf8a492be0-Metadata.json", "review": "", "metareview": "", "pdf_size": 1290965, "gs_citation": 164, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=766899766952973684&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 13, "aff": "Department of Engineering Science, University of Oxford, UK; Department of Engineering Science, University of Oxford, UK; Microsoft Research, 1 Guildhall Street, Cambridge, UK; Rolls-Royce Civil Aero-Engines, Derby, UK", "aff_domain": "robots.ox.ac.uk;robots.ox.ac.uk;scientist.com; ", "email": "robots.ox.ac.uk;robots.ox.ac.uk;scientist.com; ", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster", "aff_unique_index": "0;0;1;2", "aff_unique_norm": "University of Oxford;Microsoft;Rolls-Royce", "aff_unique_dep": "Department of Engineering Science;Microsoft Research;Civil Aero-Engines", "aff_unique_url": "https://www.ox.ac.uk;https://www.microsoft.com/en-us/research;https://www.rolls-royce.com", "aff_unique_abbr": "Oxford;MSR;RR", "aff_campus_unique_index": "1", "aff_campus_unique": ";Cambridge", "aff_country_unique_index": "0;0;0;0", "aff_country_unique": "United Kingdom" }, { "id": "47389c81e6", "title": "Temporally Dependent Plasticity: An Information Theoretic Account", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/e1314fc026da60d837353d20aefaf054-Abstract.html", "author": "Gal Chechik; Naftali Tishby", "abstract": "The paradigm of Hebbian learning has recently received a novel in(cid:173) terpretation with the discovery of synaptic plasticity that depends on the relative timing of pre and post synaptic spikes. This paper derives a temporally dependent learning rule from the basic princi(cid:173) ple of mutual information maximization and studies its relation to the experimentally observed plasticity. We find that a supervised spike-dependent learning rule sharing similar structure with the ex(cid:173) perimentally observed plasticity increases mutual information to a stable near optimal level. Moreover, the analysis reveals how the temporal structure of time-dependent learning rules is determined by the temporal filter applied by neurons over their inputs. These results suggest experimental prediction as to the dependency of the learning rule on neuronal biophysical parameters", "bibtex": "@inproceedings{NIPS2000_e1314fc0,\n author = {Chechik, Gal and Tishby, Naftali},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Temporally Dependent Plasticity: An Information Theoretic Account},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/e1314fc026da60d837353d20aefaf054-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/e1314fc026da60d837353d20aefaf054-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/e1314fc026da60d837353d20aefaf054-Metadata.json", "review": "", "metareview": "", "pdf_size": 1474660, "gs_citation": 12, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=16499275864381931261&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 9, "aff": "School of Computer Science and Engineering and the Interdisciplinary Center for Neural Computation The Hebrew University, Jerusalem, Israel; School of Computer Science and Engineering and the Interdisciplinary Center for Neural Computation The Hebrew University, Jerusalem, Israel", "aff_domain": "cs.huji.ac.il;cs.huji.ac.il", "email": "cs.huji.ac.il;cs.huji.ac.il", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Hebrew University", "aff_unique_dep": "School of Computer Science and Engineering", "aff_unique_url": "http://www.huji.ac.il", "aff_unique_abbr": "HUJI", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Jerusalem", "aff_country_unique_index": "0;0", "aff_country_unique": "Israel" }, { "id": "50a594dc24", "title": "Text Classification using String Kernels", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/68c694de94e6c110f42e587e8e48d852-Abstract.html", "author": "Huma Lodhi; John Shawe-Taylor; Nello Cristianini; Christopher J. C. H. Watkins", "abstract": "We introduce a novel kernel for comparing two text documents. The kernel is an inner product in the feature space consisting of all subsequences of length k. A subsequence is any ordered se(cid:173) quence of k characters occurring in the text though not necessarily contiguously. The subsequences are weighted by an exponentially decaying factor of their full length in the text, hence emphasising those occurrences which are close to contiguous. A direct compu(cid:173) tation of this feature vector would involve a prohibitive amount of computation even for modest values of k, since the dimension of the feature space grows exponentially with k. The paper describes how despite this fact the inner product can be efficiently evaluated by a dynamic programming technique. A preliminary experimental comparison of the performance of the kernel compared with a stan(cid:173) dard word feature space kernel results.", "bibtex": "@inproceedings{NIPS2000_68c694de,\n author = {Lodhi, Huma and Shawe-Taylor, John and Cristianini, Nello and Watkins, Christopher},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Text Classification using String Kernels},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/68c694de94e6c110f42e587e8e48d852-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/68c694de94e6c110f42e587e8e48d852-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/68c694de94e6c110f42e587e8e48d852-Metadata.json", "review": "", "metareview": "", "pdf_size": 1296153, "gs_citation": 2107, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=178373150252046887&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 27, "aff": "Department of Computer Science Royal Holloway, University of London; Department of Computer Science Royal Holloway, University of London; Department of Computer Science Royal Holloway, University of London; Department of Computer Science Royal Holloway, University of London", "aff_domain": "dcs.rhbnc.ac.uk;dcs.rhbnc.ac.uk;dcs.rhbnc.ac.uk;dcs.rhbnc.ac.uk", "email": "dcs.rhbnc.ac.uk;dcs.rhbnc.ac.uk;dcs.rhbnc.ac.uk;dcs.rhbnc.ac.uk", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0;0", "aff_unique_norm": "University of London", "aff_unique_dep": "Department of Computer Science", "aff_unique_url": "https://www.royalholloway.ac.uk", "aff_unique_abbr": "RHUL", "aff_campus_unique_index": "0;0;0;0", "aff_campus_unique": "Royal Holloway", "aff_country_unique_index": "0;0;0;0", "aff_country_unique": "United Kingdom" }, { "id": "cb82e91eeb", "title": "The Early Word Catches the Weights", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/90599c8fdd2f6e7a03ad173e2f535751-Abstract.html", "author": "Mark A. Smith; Garrison W. Cottrell; Karen L. Anderson", "abstract": "The strong correlation between the frequency of words and their naming latency has been well documented. However, as early as 1973, the Age of Acquisition (AoA) of a word was alleged to be the actual variable of interest, but these studies seem to have been ignored in most of the lit(cid:173) erature. Recently, there has been a resurgence of interest in AoA. While some studies have shown that frequency has no effect when AoA is con(cid:173) trolled for, more recent studies have found independent contributions of frequency and AoA. Connectionist models have repeatedly shown strong effects of frequency, but little attention has been paid to whether they can also show AoA effects. Indeed, several researchers have explicitly claimed that they cannot show AoA effects. In this work, we explore these claims using a simple feed forward neural network. We find a sig(cid:173) nificant contribution of AoA to naming latency, as well as conditions under which frequency provides an independent contribution.", "bibtex": "@inproceedings{NIPS2000_90599c8f,\n author = {Smith, Mark and Cottrell, Garrison and Anderson, Karen},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {The Early Word Catches the Weights},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/90599c8fdd2f6e7a03ad173e2f535751-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/90599c8fdd2f6e7a03ad173e2f535751-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/90599c8fdd2f6e7a03ad173e2f535751-Metadata.json", "review": "", "metareview": "", "pdf_size": 1387747, "gs_citation": 49, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=12970153473460028522&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 13, "aff": "Department of Computer Science, University of California at San Diego, La Jolla, CA 92093; Department of Computer Science, University of California at San Diego, La Jolla, CA 92093; Department of Computer Science, University of California at San Diego, La Jolla, CA 92093", "aff_domain": "cs.ucsd.edu;cs.ucsd.edu;cs.ucsd.edu", "email": "cs.ucsd.edu;cs.ucsd.edu;cs.ucsd.edu", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0", "aff_unique_norm": "University of California, San Diego", "aff_unique_dep": "Department of Computer Science", "aff_unique_url": "https://www.ucsd.edu", "aff_unique_abbr": "UCSD", "aff_campus_unique_index": "0;0;0", "aff_campus_unique": "La Jolla", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "ab220994a4", "title": "The Interplay of Symbolic and Subsymbolic Processes in Anagram Problem Solving", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/17c3433fecc21b57000debdf7ad5c930-Abstract.html", "author": "David B. Grimes; Michael Mozer", "abstract": "Although connectionist models have provided insights into the nature of perception and motor control, connectionist accounts of higher cognition seldom go beyond an implementation of traditional symbol-processing theories. We describe a connectionist constraint satisfaction model of how people solve anagram problems. The model exploits statistics of English orthography, but also addresses the interplay of sub symbolic and symbolic computation by a mechanism that extracts approximate symbolic representations (partial orderings of letters) from sub symbolic structures and injects the extracted representation back into the model to assist in the solution of the anagram. We show the computational benefit of this extraction-injection process and discuss its relationship to conscious mental processes and working memory. We also account for experimental data concerning the difficulty of anagram solution based on the orthographic structure of the anagram string and the target word.", "bibtex": "@inproceedings{NIPS2000_17c3433f,\n author = {Grimes, David and Mozer, Michael C},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {The Interplay of Symbolic and Subsymbolic Processes in Anagram Problem Solving},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/17c3433fecc21b57000debdf7ad5c930-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/17c3433fecc21b57000debdf7ad5c930-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/17c3433fecc21b57000debdf7ad5c930-Metadata.json", "review": "", "metareview": "", "pdf_size": 1491526, "gs_citation": 12, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=7407824131053744371&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 11, "aff": "Department of Computer Science and Institute of Cognitive Science, University of Colorado, Boulder, CO 80309-0430 USA; Department of Computer Science and Institute of Cognitive Science, University of Colorado, Boulder, CO 80309-0430 USA", "aff_domain": "cs.colorado.edu;cs.colorado.edu", "email": "cs.colorado.edu;cs.colorado.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "University of Colorado Boulder", "aff_unique_dep": "Department of Computer Science and Institute of Cognitive Science", "aff_unique_url": "https://www.colorado.edu", "aff_unique_abbr": "CU Boulder", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Boulder", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "c04771eef4", "title": "The Kernel Gibbs Sampler", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/dc40b7120e77741d191c0d2b82cea7be-Abstract.html", "author": "Thore Graepel; Ralf Herbrich", "abstract": "We present an algorithm that samples the hypothesis space of ker(cid:173) nel classifiers. Given a uniform prior over normalised weight vectors and a likelihood based on a model of label noise leads to a piece(cid:173) wise constant posterior that can be sampled by the kernel Gibbs sampler (KGS). The KGS is a Markov Chain Monte Carlo method that chooses a random direction in parameter space and samples from the resulting piecewise constant density along the line chosen. The KGS can be used as an analytical tool for the exploration of Bayesian transduction, Bayes point machines, active learning, and evidence-based model selection on small data sets that are contam(cid:173) inated with label noise. For a simple toy example we demonstrate experimentally how a Bayes point machine based on the KGS out(cid:173) performs an SVM that is incapable of taking into account label noise.", "bibtex": "@inproceedings{NIPS2000_dc40b712,\n author = {Graepel, Thore and Herbrich, Ralf},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {The Kernel Gibbs Sampler},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/dc40b7120e77741d191c0d2b82cea7be-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/dc40b7120e77741d191c0d2b82cea7be-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/dc40b7120e77741d191c0d2b82cea7be-Metadata.json", "review": "", "metareview": "", "pdf_size": 1183418, "gs_citation": 30, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=7631774188623815586&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 7, "aff": "Statistics Research Group, Computer Science Department, Technical University of Berlin, Berlin, Germany; Statistics Research Group, Computer Science Department, Technical University of Berlin, Berlin, Germany", "aff_domain": "cs.tu-berlin.de;cs.tu-berlin.de", "email": "cs.tu-berlin.de;cs.tu-berlin.de", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Technical University of Berlin", "aff_unique_dep": "Computer Science Department", "aff_unique_url": "https://www.tu-berlin.de", "aff_unique_abbr": "TU Berlin", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Berlin", "aff_country_unique_index": "0;0", "aff_country_unique": "Germany" }, { "id": "b1bb8b1fdc", "title": "The Kernel Trick for Distances", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/4e87337f366f72daa424dae11df0538c-Abstract.html", "author": "Bernhard Sch\u00f6lkopf", "abstract": "A method is described which, like the kernel trick in support vector ma(cid:173) chines (SVMs), lets us generalize distance-based algorithms to operate in feature spaces, usually nonlinearly related to the input space. This is done by identifying a class of kernels which can be represented as norm-based distances in Hilbert spaces. It turns out that common kernel algorithms, such as SVMs and kernel PCA, are actually really distance based algorithms and can be run with that class of kernels, too. As well as providing a useful new insight into how these algorithms work, the present work can form the basis for conceiving new algorithms.", "bibtex": "@inproceedings{NIPS2000_4e87337f,\n author = {Sch\\\"{o}lkopf, Bernhard},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {The Kernel Trick for Distances},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/4e87337f366f72daa424dae11df0538c-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/4e87337f366f72daa424dae11df0538c-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/4e87337f366f72daa424dae11df0538c-Metadata.json", "review": "", "metareview": "", "pdf_size": 1290426, "gs_citation": 1002, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=99808863764751706&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 12, "aff": "Microsoft Research", "aff_domain": "kyb.tuebingen.mpg.de", "email": "kyb.tuebingen.mpg.de", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster", "aff_unique_index": "0", "aff_unique_norm": "Microsoft", "aff_unique_dep": "Microsoft Research", "aff_unique_url": "https://www.microsoft.com/en-us/research", "aff_unique_abbr": "MSR", "aff_country_unique_index": "0", "aff_country_unique": "United States" }, { "id": "b97dc618ce", "title": "The Manhattan World Assumption: Regularities in Scene Statistics which Enable Bayesian Inference", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/90e1357833654983612fb05e3ec9148c-Abstract.html", "author": "James M. Coughlan; Alan L. Yuille", "abstract": "Preliminary work by the authors made use of the so-called \"Man(cid:173) hattan world\" assumption about the scene statistics of city and indoor scenes. This assumption stated that such scenes were built on a cartesian grid which led to regularities in the image edge gra(cid:173) dient statistics. In this paper we explore the general applicability of this assumption and show that, surprisingly, it holds in a large variety of less structured environments including rural scenes. This enables us, from a single image, to determine the orientation of the viewer relative to the scene structure and also to detect target ob(cid:173) jects which are not aligned with the grid. These inferences are performed using a Bayesian model with probability distributions (e.g. on the image gradient statistics) learnt from real data.", "bibtex": "@inproceedings{NIPS2000_90e13578,\n author = {Coughlan, James and Yuille, Alan L},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {The Manhattan World Assumption: Regularities in Scene Statistics which Enable Bayesian Inference},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/90e1357833654983612fb05e3ec9148c-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/90e1357833654983612fb05e3ec9148c-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/90e1357833654983612fb05e3ec9148c-Metadata.json", "review": "", "metareview": "", "pdf_size": 1344728, "gs_citation": 204, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=14593617026483612180&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 12, "aff": "Smith-Kettlewell Eye Research Inst.; Smith-Kettlewell Eye Research Inst.", "aff_domain": "ski.org;ski.org", "email": "ski.org;ski.org", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Smith-Kettlewell Eye Research Institute", "aff_unique_dep": "Eye Research", "aff_unique_url": "https://www.ski.org", "aff_unique_abbr": "SKI", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "a1cdc52bd2", "title": "The Missing Link - A Probabilistic Model of Document Content and Hypertext Connectivity", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f45a1078feb35de77d26b3f7a52ef502-Abstract.html", "author": "David A. Cohn; Thomas Hofmann", "abstract": "We describe a joint probabilistic model for modeling the contents and inter-connectivity of document collections such as sets of web pages or research paper archives. The model is based on a probabilistic factor decomposition and allows identifying principal topics of the collection as well as authoritative documents within those topics. Furthermore, the relationships between topics is mapped out in order to build a predictive model of link content. Among the many applications of this approach are information retrieval and search, topic identification, query disambigua(cid:173) tion, focused web crawling, web authoring, and bibliometric analysis.", "bibtex": "@inproceedings{NIPS2000_f45a1078,\n author = {Cohn, David and Hofmann, Thomas},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {The Missing Link - A Probabilistic Model of Document Content and Hypertext Connectivity},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f45a1078feb35de77d26b3f7a52ef502-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f45a1078feb35de77d26b3f7a52ef502-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f45a1078feb35de77d26b3f7a52ef502-Metadata.json", "review": "", "metareview": "", "pdf_size": 1439684, "gs_citation": 653, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=7330141684043959110&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 21, "aff": "Burning Glass Technologies; Department of Computer Science, Brown University", "aff_domain": "burning-glass.com;cs.brown.edu", "email": "burning-glass.com;cs.brown.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "Burning Glass Technologies;Brown University", "aff_unique_dep": ";Department of Computer Science", "aff_unique_url": "https://www.burning-glass.com;https://www.brown.edu", "aff_unique_abbr": ";Brown", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "50b89befb2", "title": "The Unscented Particle Filter", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f5c3dd7514bf620a1b85450d2ae374b1-Abstract.html", "author": "Rudolph van der Merwe; Arnaud Doucet; Nando de Freitas; Eric A. Wan", "abstract": "In this paper, we propose a new particle filter based on sequential importance sampling. The algorithm uses a bank of unscented fil(cid:173) ters to obtain the importance proposal distribution. This proposal has two very \"nice\" properties. Firstly, it makes efficient use of the latest available information and, secondly, it can have heavy tails. As a result, we find that the algorithm outperforms stan(cid:173) dard particle filtering and other nonlinear filtering methods very substantially. This experimental finding is in agreement with the theoretical convergence proof for the algorithm. The algorithm also includes resampling and (possibly) Markov chain Monte Carlo (MCMC) steps.", "bibtex": "@inproceedings{NIPS2000_f5c3dd75,\n author = {van der Merwe, Rudolph and Doucet, Arnaud and de Freitas, Nando and Wan, Eric},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {The Unscented Particle Filter},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f5c3dd7514bf620a1b85450d2ae374b1-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f5c3dd7514bf620a1b85450d2ae374b1-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f5c3dd7514bf620a1b85450d2ae374b1-Metadata.json", "review": "", "metareview": "", "pdf_size": 1197036, "gs_citation": 2625, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=14617522201435748952&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 23, "aff": ";;;", "aff_domain": ";;;", "email": ";;;", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster" }, { "id": "c1db780765", "title": "The Use of Classifiers in Sequential Inference", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f4a4da9aa7eadfd23c7bdb7cf57b3112-Abstract.html", "author": "Vasin Punyakanok; Dan Roth", "abstract": "We study the problem of combining the outcomes of several different classifiers in a way that provides a coherent inference that satisfies some constraints. In particular, we develop two general approaches for an im(cid:173) portant subproblem - identifying phrase structure. The first is a Marko(cid:173) vian approach that extends standard HMMs to allow the use of a rich ob(cid:173) servation structure and of general classifiers to model state-observation dependencies. The second is an extension of constraint satisfaction for(cid:173) malisms. We develop efficient combination algorithms under both mod(cid:173) els and study them experimentally in the context of shallow parsing.", "bibtex": "@inproceedings{NIPS2000_f4a4da9a,\n author = {Punyakanok, Vasin and Roth, Dan},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {The Use of Classifiers in Sequential Inference},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f4a4da9aa7eadfd23c7bdb7cf57b3112-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f4a4da9aa7eadfd23c7bdb7cf57b3112-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f4a4da9aa7eadfd23c7bdb7cf57b3112-Metadata.json", "review": "", "metareview": "", "pdf_size": 1623041, "gs_citation": 272, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=2456823486766507333&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 13, "aff": "Department of Computer Science, University of Illinois at Urbana-Champaign; Department of Computer Science, University of Illinois at Urbana-Champaign", "aff_domain": "cs.uiuc.edu;cs.uiuc.edu", "email": "cs.uiuc.edu;cs.uiuc.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "University of Illinois Urbana-Champaign", "aff_unique_dep": "Department of Computer Science", "aff_unique_url": "https://illinois.edu", "aff_unique_abbr": "UIUC", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Urbana-Champaign", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" }, { "id": "bd958f3f85", "title": "The Use of MDL to Select among Computational Models of Cognition", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/af3303f852abeccd793068486a391626-Abstract.html", "author": "In Jae Myung; Mark A. Pitt; Shaobo Zhang; Vijay Balasubramanian", "abstract": "How should we decide among competing explanations of a cognitive process given limited observations? The problem of model selection is at the heart of progress in cognitive science. In this paper, Minimum Description Length (MDL) is introduced as a method for selecting among computational models of cognition. We also show that differential geometry provides an intuitive understanding of what drives model selection in MDL. Finally, adequacy of MDL is demonstrated in two areas of cognitive modeling.", "bibtex": "@inproceedings{NIPS2000_af3303f8,\n author = {Myung, In and Pitt, Mark and Zhang, Shaobo and Balasubramanian, Vijay},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {The Use of MDL to Select among Computational Models of Cognition},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/af3303f852abeccd793068486a391626-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/af3303f852abeccd793068486a391626-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/af3303f852abeccd793068486a391626-Metadata.json", "review": "", "metareview": "", "pdf_size": 1361592, "gs_citation": 19, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=12446998701948709712&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 7, "aff": ";;;", "aff_domain": ";;;", "email": ";;;", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster" }, { "id": "9174e3669d", "title": "Tree-Based Modeling and Estimation of Gaussian Processes on Graphs with Cycles", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/a3545bd79d31f9a72d3a78690adf73fc-Abstract.html", "author": "Martin J. Wainwright; Erik B. Sudderth; Alan S. Willsky", "abstract": "We present the embedded trees algorithm, an iterative technique for estimation of Gaussian processes defined on arbitrary graphs. By exactly solving a series of modified problems on embedded span(cid:173) ning trees, it computes the conditional means with an efficiency comparable to or better than other techniques. Unlike other meth(cid:173) ods, the embedded trees algorithm also computes exact error co(cid:173) variances. The error covariance computation is most efficient for graphs in which removing a small number of edges reveals an em(cid:173) bedded tree. In this context, we demonstrate that sparse loopy graphs can provide a significant increase in modeling power rela(cid:173) tive to trees, with only a minor increase in estimation complexity.", "bibtex": "@inproceedings{NIPS2000_a3545bd7,\n author = {Wainwright, Martin J and Sudderth, Erik and Willsky, Alan},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Tree-Based Modeling and Estimation of Gaussian Processes on Graphs with Cycles},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/a3545bd79d31f9a72d3a78690adf73fc-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/a3545bd79d31f9a72d3a78690adf73fc-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/a3545bd79d31f9a72d3a78690adf73fc-Metadata.json", "review": "", "metareview": "", "pdf_size": 1395550, "gs_citation": 36, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=254382567704810244&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 15, "aff": "Laboratory for Information and Decision Systems; Laboratory for Information and Decision Systems; Laboratory for Information and Decision Systems", "aff_domain": "mit.edu;mit.edu;mit.edu", "email": "mit.edu;mit.edu;mit.edu", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;0;0", "aff_unique_norm": "Massachusetts Institute of Technology", "aff_unique_dep": "Laboratory for Information and Decision Systems", "aff_unique_url": "http://web.mit.edu/lids", "aff_unique_abbr": "LIDS", "aff_campus_unique_index": "0;0;0", "aff_campus_unique": "Cambridge", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "cfb0548273", "title": "Universality and Individuality in a Neural Code", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/5fa9e41bfec0725742cc9d15ef594120-Abstract.html", "author": "Elad Schneidman; Naama Brenner; Naftali Tishby; Robert R. de Ruyter van Steveninck; William Bialek", "abstract": "The problem of neural coding is to understand how sequences of action potentials (spikes) are related to sensory stimuli, motor out(cid:173) puts, or (ultimately) thoughts and intentions. One clear question is whether the same coding rules are used by different neurons, or by corresponding neurons in different individuals. We present a quantitative formulation of this problem using ideas from informa(cid:173) tion theory, and apply this approach to the analysis of experiments in the fly visual system. We find significant individual differences in the structure of the code, particularly in the way that tempo(cid:173) ral patterns of spikes are used to convey information beyond that available from variations in spike rate. On the other hand, all the flies in our ensemble exhibit a high coding efficiency, so that every spike carries the same amount of information in all the individuals. Thus the neural code has a quantifiable mixture of individuality and universality.", "bibtex": "@inproceedings{NIPS2000_5fa9e41b,\n author = {Schneidman, Elad and Brenner, Naama and Tishby, Naftali and van Steveninck, Robert and Bialek, William},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Universality and Individuality in a Neural Code},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/5fa9e41bfec0725742cc9d15ef594120-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/5fa9e41bfec0725742cc9d15ef594120-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/5fa9e41bfec0725742cc9d15ef594120-Metadata.json", "review": "", "metareview": "", "pdf_size": 1404763, "gs_citation": 35, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=3035050787985848907&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 23, "aff": "ISchool of Computer Science and Engineering, Center for Neural Computation; Department of Neurobiology, Hebrew University, Jerusalem 91904, Israel; NEC Research Institute, 4 Independence Way, Princeton, New Jersey 08540, USA; NEC Research Institute, 4 Independence Way, Princeton, New Jersey 08540, USA; NEC Research Institute, 4 Independence Way, Princeton, New Jersey 08540, USA", "aff_domain": "cs.huji.ac.il;cs.huji.ac.il;research.nj.nec.com;research.nj.nec.com;research.nj.nec.com", "email": "cs.huji.ac.il;cs.huji.ac.il;research.nj.nec.com;research.nj.nec.com;research.nj.nec.com", "github": "", "project": "", "author_num": 5, "track": "main", "status": "Poster", "aff_unique_index": "0;1;2;2;2", "aff_unique_norm": "School of Computer Science and Engineering;Hebrew University;NEC Research Institute", "aff_unique_dep": "Center for Neural Computation;Department of Neurobiology;", "aff_unique_url": ";http://www.huji.ac.il;https://www.neci.nec.com", "aff_unique_abbr": ";HUJI;NECRI", "aff_campus_unique_index": "1;2;2;2", "aff_campus_unique": ";Jerusalem;Princeton", "aff_country_unique_index": "0;1;0;0;0", "aff_country_unique": "United States;Israel" }, { "id": "e027bcc9e6", "title": "Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/2d1b2a5ff364606ff041650887723470-Abstract.html", "author": "Brian Sallans; Geoffrey E. Hinton", "abstract": "The problem of reinforcement learning in large factored Markov decision processes is explored. The Q-value of a state-action pair is approximated by the free energy of a product of experts network. Network parameters are learned on-line using a modified SARSA algorithm which minimizes the inconsistency of the Q-values of consecutive state-action pairs. Ac(cid:173) tions are chosen based on the current value estimates by fixing the current state and sampling actions from the network using Gibbs sampling. The algorithm is tested on a co-operative multi-agent task. The product of experts model is found to perform comparably to table-based Q-Iearning for small instances of the task, and continues to perform well when the problem becomes too large for a table-based representation.", "bibtex": "@inproceedings{NIPS2000_2d1b2a5f,\n author = {Sallans, Brian and Hinton, Geoffrey E},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/2d1b2a5ff364606ff041650887723470-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/2d1b2a5ff364606ff041650887723470-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/2d1b2a5ff364606ff041650887723470-Metadata.json", "review": "", "metareview": "", "pdf_size": 1369128, "gs_citation": 35, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=9235534049305198865&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 15, "aff": "Department of Computer Science, University of Toronto; Gatsby Computational Neuroscience Unit, University College London", "aff_domain": "cs.toronto.edu;gatsby.ucl.ac.uk", "email": "cs.toronto.edu;gatsby.ucl.ac.uk", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;1", "aff_unique_norm": "University of Toronto;University College London", "aff_unique_dep": "Department of Computer Science;Gatsby Computational Neuroscience Unit", "aff_unique_url": "https://www.utoronto.ca;https://www.ucl.ac.uk", "aff_unique_abbr": "U of T;UCL", "aff_campus_unique_index": "0;1", "aff_campus_unique": "Toronto;London", "aff_country_unique_index": "0;1", "aff_country_unique": "Canada;United Kingdom" }, { "id": "448d998021", "title": "Using the Nystr\u00f6m Method to Speed Up Kernel Machines", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/19de10adbaa1b2ee13f77f679fa1483a-Abstract.html", "author": "Christopher K. I. Williams; Matthias Seeger", "abstract": "Abstract Unavailable", "bibtex": "@inproceedings{NIPS2000_19de10ad,\n author = {Williams, Christopher and Seeger, Matthias},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Using the Nystr\\\"{o}m Method to Speed Up Kernel Machines},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/19de10adbaa1b2ee13f77f679fa1483a-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/19de10adbaa1b2ee13f77f679fa1483a-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/19de10adbaa1b2ee13f77f679fa1483a-Metadata.json", "review": "", "metareview": "", "pdf_size": 407958, "gs_citation": 3227, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=13318970617132675642&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 9, "aff": ";", "aff_domain": ";", "email": ";", "github": "https://github.com/deepnlp-project", "project": "https://deepnlp-project.org", "author_num": 2, "track": "main", "status": "Poster" }, { "id": "7ae4696f11", "title": "Vicinal Risk Minimization", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/ba9a56ce0a9bfa26e8ed9e10b2cc8f46-Abstract.html", "author": "Olivier Chapelle; Jason Weston; L\u00e9on Bottou; Vladimir Vapnik", "abstract": "The Vicinal Risk Minimization principle establishes a bridge between generative models and methods derived from the Structural Risk Mini(cid:173) mization Principle such as Support Vector Machines or Statistical Reg(cid:173) ularization. We explain how VRM provides a framework which inte(cid:173) grates a number of existing algorithms, such as Parzen windows, Support Vector Machines, Ridge Regression, Constrained Logistic Classifiers and Tangent-Prop. We then show how the approach implies new algorithm(cid:173) s for solving problems usually associated with generative models. New algorithms are described for dealing with pattern recognition problems with very different pattern distributions and dealing with unlabeled data. Preliminary empirical results are presented.", "bibtex": "@inproceedings{NIPS2000_ba9a56ce,\n author = {Chapelle, Olivier and Weston, Jason and Bottou, L\\'{e}on and Vapnik, Vladimir},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Vicinal Risk Minimization},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/ba9a56ce0a9bfa26e8ed9e10b2cc8f46-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/ba9a56ce0a9bfa26e8ed9e10b2cc8f46-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/ba9a56ce0a9bfa26e8ed9e10b2cc8f46-Metadata.json", "review": "", "metareview": "", "pdf_size": 1300171, "gs_citation": 454, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=14073358896088151472&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 12, "aff": "AT&T Research Labs, 100 Schultz drive, Red Bank, NJ, USA; AT&T Research Labs, 100 Schultz drive, Red Bank, NJ, USA + Barnhill BioInformatics.com, Savannah, GA, USA; AT&T Research Labs, 100 Schultz drive, Red Bank, NJ, USA; AT&T Research Labs, 100 Schultz drive, Red Bank, NJ, USA", "aff_domain": "research.att.com;research.att.com;research.att.com;research.att.com", "email": "research.att.com;research.att.com;research.att.com;research.att.com", "github": "", "project": "", "author_num": 4, "track": "main", "status": "Poster", "aff_unique_index": "0;0+1;0;0", "aff_unique_norm": "AT&T Research Labs;Barnhill Bioinformatics", "aff_unique_dep": ";", "aff_unique_url": "https://www.att.com/research;", "aff_unique_abbr": "AT&T;", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0+0;0;0", "aff_country_unique": "United States" }, { "id": "b79a8092ad", "title": "Weak Learners and Improved Rates of Convergence in Boosting", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/dea9ddb25cbf2352cf4dec30222a02a5-Abstract.html", "author": "Shie Mannor; Ron Meir", "abstract": "The problem of constructing weak classifiers for boosting algo(cid:173) rithms is studied. We present an algorithm that produces a linear classifier that is guaranteed to achieve an error better than random guessing for any distribution on the data. While this weak learner is not useful for learning in general, we show that under reasonable conditions on the distribution it yields an effective weak learner for one-dimensional problems. Preliminary simulations suggest that similar behavior can be expected in higher dimensions, a result which is corroborated by some recent theoretical bounds. Addi(cid:173) tionally, we provide improved convergence rate bounds for the gen(cid:173) eralization error in situations where the empirical error can be made small, which is exactly the situation that occurs if weak learners with guaranteed performance that is better than random guessing can be established.", "bibtex": "@inproceedings{NIPS2000_dea9ddb2,\n author = {Mannor, Shie and Meir, Ron},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Weak Learners and Improved Rates of Convergence in Boosting},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/dea9ddb25cbf2352cf4dec30222a02a5-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/dea9ddb25cbf2352cf4dec30222a02a5-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/dea9ddb25cbf2352cf4dec30222a02a5-Metadata.json", "review": "", "metareview": "", "pdf_size": 1515634, "gs_citation": 16, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=7423995277105205876&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 7, "aff": "Department of Electrical Engineering, Technion, Haifa 32000, Israel; Department of Electrical Engineering, Technion, Haifa 32000, Israel", "aff_domain": "techunix.technion.ac.il;ee.technion.ac.il", "email": "techunix.technion.ac.il;ee.technion.ac.il", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Technion", "aff_unique_dep": "Department of Electrical Engineering", "aff_unique_url": "https://www.technion.ac.il", "aff_unique_abbr": "Technion", "aff_campus_unique_index": "0;0", "aff_campus_unique": "Haifa", "aff_country_unique_index": "0;0", "aff_country_unique": "Israel" }, { "id": "f4c9dd6498", "title": "What Can a Single Neuron Compute?", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/a19acd7d2689207f9047f8cb01357370-Abstract.html", "author": "Blaise Ag\u00fcera y Arcas; Adrienne L. Fairhall; William Bialek", "abstract": "In this paper we formulate a description of the computation per(cid:173) formed by a neuron as a combination of dimensional reduction and nonlinearity. We implement this description for the Hodgkin(cid:173) Huxley model, identify the most relevant dimensions and find the nonlinearity. A two dimensional description already captures a significant fraction of the information that spikes carry about dy(cid:173) namic inputs. This description also shows that computation in the Hodgkin-Huxley model is more complex than a simple integrate(cid:173) and-fire or perceptron model.", "bibtex": "@inproceedings{NIPS2000_a19acd7d,\n author = {Ag\\\"{u}era y Arcas, Blaise and Fairhall, Adrienne and Bialek, William},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {What Can a Single Neuron Compute?},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/a19acd7d2689207f9047f8cb01357370-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/a19acd7d2689207f9047f8cb01357370-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/a19acd7d2689207f9047f8cb01357370-Metadata.json", "review": "", "metareview": "", "pdf_size": 1329509, "gs_citation": 30, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=11513866085209461473&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 6, "aff": "Rare Books Library, Princeton University; NEC Research Institute; NEC Research Institute", "aff_domain": "prineeton.edu;researeh.nj.nee.com;researeh.nj.nee.com", "email": "prineeton.edu;researeh.nj.nee.com;researeh.nj.nee.com", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;1;1", "aff_unique_norm": "Princeton University;NEC Research Institute", "aff_unique_dep": "Rare Books Library;", "aff_unique_url": "https://www.princeton.edu;https://www.neclab.eu", "aff_unique_abbr": "Princeton;NEC RI", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0;0", "aff_country_unique": "United States" }, { "id": "560b010764", "title": "Whence Sparseness?", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/f0fcf351df4eb6786e9bb6fc4e2dee02-Abstract.html", "author": "Carl van Vreeswijk", "abstract": "It has been shown that the receptive fields of simple cells in VI can be ex(cid:173) plained by assuming optimal encoding, provided that an extra constraint of sparseness is added. This finding suggests that there is a reason, in(cid:173) dependent of optimal representation, for sparseness. However this work used an ad hoc model for the noise. Here I show that, if a biologically more plausible noise model, describing neurons as Poisson processes, is used sparseness does not have to be added as a constraint. Thus I con(cid:173) clude that sparseness is not a feature that evolution has striven for, but is simply the result of the evolutionary pressure towards an optimal repre(cid:173) sentation.", "bibtex": "@inproceedings{NIPS2000_f0fcf351,\n author = {van Vreeswijk, Carl},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Whence Sparseness?},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/f0fcf351df4eb6786e9bb6fc4e2dee02-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/f0fcf351df4eb6786e9bb6fc4e2dee02-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/f0fcf351df4eb6786e9bb6fc4e2dee02-Metadata.json", "review": "", "metareview": "", "pdf_size": 1155700, "gs_citation": 11, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=13812656138323616814&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 8, "aff": "", "aff_domain": "", "email": "", "github": "", "project": "", "author_num": 1, "track": "main", "status": "Poster" }, { "id": "93c6dcf8f9", "title": "Who Does What? A Novel Algorithm to Determine Function Localization", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/0533a888904bd4867929dffd884d60b8-Abstract.html", "author": "Ranit Aharonov-Barki; Isaac Meilijson; Eytan Ruppin", "abstract": "We introduce a novel algorithm, termed PPA (Performance Prediction Algorithm), that quantitatively measures the contributions of elements of a neural system to the tasks it performs. The algorithm identifies the neurons or areas which participate in a cognitive or behavioral task, given data about performance decrease in a small set of lesions. It also allows the accurate prediction of performances due to multi-element lesions. The effectiveness of the new algorithm is demonstrated in two models of recurrent neural networks with complex interactions among the ele(cid:173) ments. The algorithm is scalable and applicable to the analysis of large neural networks. Given the recent advances in reversible inactivation techniques, it has the potential to significantly contribute to the under(cid:173) standing of the organization of biological nervous systems, and to shed light on the long-lasting debate about local versus distributed computa(cid:173) tion in the brain.", "bibtex": "@inproceedings{NIPS2000_0533a888,\n author = {Aharonov-Barki, Ranit and Meilijson, Isaac and Ruppin, Eytan},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {Who Does What? A Novel Algorithm to Determine Function Localization},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/0533a888904bd4867929dffd884d60b8-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/0533a888904bd4867929dffd884d60b8-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/0533a888904bd4867929dffd884d60b8-Metadata.json", "review": "", "metareview": "", "pdf_size": 1378786, "gs_citation": 1, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=9404478699556845337&as_sdt=5,33&sciodt=0,33&hl=en", "gs_version_total": 12, "aff": "Interdisciplinary Center for Neural Computation, The Hebrew University, Jerusalem 91904, Israel; School of Mathematical Sciences, Tel-Aviv University, Tel-Aviv, Israel; School of Mathematical Sciences, Tel-Aviv University, Tel-Aviv, Israel", "aff_domain": "alice.nc.huji.ac.il;math.tau.ac.il;math.tau.ac.il", "email": "alice.nc.huji.ac.il;math.tau.ac.il;math.tau.ac.il", "github": "", "project": "", "author_num": 3, "track": "main", "status": "Poster", "aff_unique_index": "0;1;1", "aff_unique_norm": "Hebrew University;Tel-Aviv University", "aff_unique_dep": "Interdisciplinary Center for Neural Computation;School of Mathematical Sciences", "aff_unique_url": "http://www.huji.ac.il;https://www.tau.ac.il", "aff_unique_abbr": "HUJI;TAU", "aff_campus_unique_index": "0;1;1", "aff_campus_unique": "Jerusalem;Tel-Aviv", "aff_country_unique_index": "0;0;0", "aff_country_unique": "Israel" }, { "id": "01b4f7242e", "title": "`N-Body' Problems in Statistical Learning", "site": "https://papers.nips.cc/paper_files/paper/2000/hash/7385db9a3f11415bc0e9e2625fae3734-Abstract.html", "author": "Alexander G. Gray; Andrew W. Moore", "abstract": "We present efficient algorithms for all-point-pairs problems , or 'N(cid:173) body '-like problems, which are ubiquitous in statistical learning. We focus on six examples, including nearest-neighbor classification, kernel density estimation, outlier detection , and the two-point correlation. These include any problem which abstractly requires a comparison of each of the N points in a dataset with each other point and would naively be solved using N 2 distance computations. In practice N is often large enough to make this infeasible. We present a suite of new geometric t echniques which are applicable in principle to any 'N-body' computation including large-scale mixtures of Gaussians, RBF neural networks, and HMM 's. Our algorithms exhibit favorable asymptotic scaling and are empirically several orders of magnitude faster than the naive computation, even for small datasets. We are aware of no exact algorithms for these problems which are more effi(cid:173) cient either empirically or theoretically. In addition, our framework yields simple and elegant algorithms. It also permits two important generalizations beyond the standard all-point-pairs problems, which are more difficult. These are represented by our final examples, the multiple two-point correlation and the notorious n-point correlation.", "bibtex": "@inproceedings{NIPS2000_7385db9a,\n author = {Gray, Alexander and Moore, Andrew},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {T. Leen and T. Dietterich and V. Tresp},\n pages = {},\n publisher = {MIT Press},\n title = {\\textasciigrave N-Body\\textquotesingle Problems in Statistical Learning},\n url = {https://proceedings.neurips.cc/paper_files/paper/2000/file/7385db9a3f11415bc0e9e2625fae3734-Paper.pdf},\n volume = {13},\n year = {2000}\n}", "pdf": "https://papers.nips.cc/paper_files/paper/2000/file/7385db9a3f11415bc0e9e2625fae3734-Paper.pdf", "supp": "", "metadata": "https://papers.nips.cc/paper_files/paper/2000/file/7385db9a3f11415bc0e9e2625fae3734-Metadata.json", "review": "", "metareview": "", "pdf_size": 1498935, "gs_citation": 389, "gs_cited_by_link": "https://scholar.google.com/scholar?cites=6603163528125522685&as_sdt=2005&sciodt=0,5&hl=en", "gs_version_total": 9, "aff": "Department of Computer Science, Carnegie Mellon University; Robotics Inst. and Dept. Compo Sci., Carnegie Mellon University", "aff_domain": "cs.cmu.edu;cs.cmu.edu", "email": "cs.cmu.edu;cs.cmu.edu", "github": "", "project": "", "author_num": 2, "track": "main", "status": "Poster", "aff_unique_index": "0;0", "aff_unique_norm": "Carnegie Mellon University", "aff_unique_dep": "Department of Computer Science", "aff_unique_url": "https://www.cmu.edu", "aff_unique_abbr": "CMU", "aff_campus_unique_index": "", "aff_campus_unique": "", "aff_country_unique_index": "0;0", "aff_country_unique": "United States" } ]