Table of Contents

• Who Does What? A Novel Algorithm to Determine Function LocalizationRanit Aharonov-Barki, Isaac Meilijson, Eytan Ruppin. 3-9
• A Productive, Systematic Framework for the Representation of Visual StructureShimon Edelman, Nathan Intrator. 10-16
• The Interplay of Symbolic and Subsymbolic Processes in Anagram Problem SolvingDavid B. Grimes, Michael Mozer. 17-23
• Hippocampally-Dependent Consolidation in a Hierarchical Model of NeocortexSzabolcs Káli, Peter Dayan. 24-30
• Position Variance, Recurrence and Perceptual LearningZhaoping Li, Peter Dayan. 31-37
• The Use of MDL to Select among Computational Models of CognitionIn Jae Myung, Mark A. Pitt, Shaobo Zhang, Vijay Balasubramanian. 38-44
• Active Inference in Concept LearningJonathan D. Nelson, Javier R. Movellan. 45-51
• The Early Word Catches the WeightsMark A. Smith, Garrison W. Cottrell, Karen L. Anderson. 52-58
• Structure Learning in Human Causal InductionJoshua B. Tenenbaum, Thomas L. Griffiths. 59-65
• Adaptive Object Representation with Hierarchically-Distributed Memory SitesBosco S. Tjan. 66-72
• What Can a Single Neuron Compute?Blaise Agüera y Arcas, Adrienne L. Fairhall, William Bialek. 75-81
• Dendritic Compartmentalization Could Underlie Competition and Attentional Biasing of Simultaneous Visual StimuliKevin A. Archie, Bartlett W. Mel. 82-88
• Place Cells and Spatial Navigation Based on 2D Visual Feature Extraction, Path Integration, and Reinforcement LearningAngelo Arleo, Fabrizio Smeraldi, Stéphane Hug, Wulfram Gerstner. 89-95
• Modelling Spatial Recall, Mental Imagery and NeglectSuzanna Becker, Neil Burgess. 96-102
• Stability and Noise in Biochemical SwitchesWilliam Bialek. 103-109
• Temporally Dependent Plasticity: An Information Theoretic AccountGal Chechik, Naftali Tishby. 110-116
• A New Model of Spatial Representation in Multimodal Brain AreasSophie Deneve, Jean-Rene Duhamel, Alexandre Pouget. 117-123
• Multiple Timescales of Adaptation in a Neural CodeAdrienne L. Fairhall, Geoffrey D. Lewen, William Bialek, Robert R. de Ruyter van Steveninck. 124-130
• Dopamine BonusesSham Kakade, Peter Dayan. 131-137
• Finding the Key to a SynapseThomas Natschläger, Wolfgang Maass. 138-144
• Processing of Time Series by Neural Circuits with Biologically Realistic Synaptic DynamicsThomas Natschläger, Wolfgang Maass, Eduardo D. Sontag, Anthony M. Zador. 145-151
• Spike-Timing-Dependent Learning for Oscillatory NetworksSilvia Scarpetta, Zhaoping Li, John A. Hertz. 152-158
• Universality and Individuality in a Neural CodeElad Schneidman, Naama Brenner, Naftali Tishby, Robert R. de Ruyter van Steveninck, William Bialek. 159-165
• Natural Sound Statistics and Divisive Normalization in the Auditory SystemOdelia Schwartz, Eero P. Simoncelli. 166-172
• Development of Hybrid Systems: Interfacing a Silicon Neuron to a Leech Heart InterneuronMario F. Simoni, Gennady S. Cymbalyuk, Michael E. Sorensen, Ronald L. Calabrese, Stephen P. DeWeerth. 173-179
• Whence Sparseness?Carl van Vreeswijk. 180-186
• Efficient Learning of Linear PerceptronsShai Ben-David, Hans-Ulrich Simon. 189-195
• Algorithmic Stability and Generalization PerformanceOlivier Bousquet, André Elisseeff. 196-202
• Competition and Arbors in Ocular DominancePeter Dayan. 203-209
• From Margin to SparsityThore Graepel, Ralf Herbrich, Robert C. Williamson. 210-216
• Permitted and Forbidden Sets in Symmetric Threshold-Linear NetworksRichard H. R. Hahnloser, H. Sebastian Seung. 217-223
• A PAC-Bayesian Margin Bound for Linear Classifiers: Why SVMs workRalf Herbrich, Thore Graepel. 224-230
• On Reversing Jensen s InequalityTony Jebara, Alex Pentland. 231-237
• Second Order Approximations for Probability ModelsHilbert J. Kappen, Wim Wiegerinck. 238-244
• Some New Bounds on the Generalization Error of Combined ClassifiersVladimir Koltchinskii, Dmitriy Panchenko, Fernando Lozano. 245-251
• Sparsity of Data Representation of Optimal Kernel Machine and Leave-one-out EstimatorAdam Kowalczyk. 252-258
• Foundations for a Circuit Complexity Theory of Sensory ProcessingRobert A. Legenstein, Wolfgang Maass. 259-265
• A Tighter Bound for Graphical ModelsMartijn A. R. Leisink, Hilbert J. Kappen. 266-272
• Learning Curves for Gaussian Processes Regression: A Framework for Good ApproximationsDörthe Malzahn, Manfred Opper. 273-279
• Weak Learners and Improved Rates of Convergence in BoostingShie Mannor, Ron Meir. 280-286
• Learning Continuous Distributions: Simulations With Field Theoretic PriorsIlya Nemenman, William Bialek. 287-293
• Occam s RazorCarl Edward Rasmussen, Zoubin Ghahramani. 294-300
• The Kernel Trick for DistancesBernhard Schölkopf. 301-307
• Regularization with Dot-Product KernelsAlex J. Smola, Zoltán L. Óvári, Robert C. Williamson. 308-314
• Analysis of Bit Error Probability of Direct-Sequence CDMA Multiuser DemodulatorsToshiyuki Tanaka. 315-321
• Error-correcting Codes on a Bethe-like LatticeRenato Vicente, David Saad, Yoshiyuki Kabashima. 322-328
• Algebraic Information Geometry for Learning Machines with SingularitiesSumio Watanabe. 329-335
• Computing with Finite and Infinite NetworksOle Winther. 336-342
• Stagewise Processing in Error-correcting Codes and Image RestorationK. Y. Michael Wong, Hidetoshi Nishimori. 343-349
• Learning Winner-take-all Competition Between Groups of Neurons in Lateral Inhibitory NetworksXiaohui Xie, Richard H. R. Hahnloser, H. Sebastian Seung. 350-356
• Convergence of Large Margin Separable Linear ClassificationTong Zhang. 357-363
• A Support Vector Method for ClusteringAsa Ben-Hur, David Horn, Hava T. Siegelmann, Vladimir Vapnik. 367-373
• A Variational Mean-Field Theory for Sigmoidal Belief NetworksChiranjib Bhattacharyya, S. Sathiya Keerthi. 374-380
• Direct Classification with Indirect DataTimothy X. Brown. 381-387
• Model Complexity, Goodness of Fit and Diminishing ReturnsIgor V. Cadez, Padhraic Smyth. 388-394
• A Linear Programming Approach to Novelty DetectionColin Campbell, Kristin P. Bennett. 395-401
• Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early StoppingRich Caruana, Steve Lawrence, C. Lee Giles. 402-408
• Incremental and Decremental Support Vector Machine LearningGert Cauwenberghs, Tomaso Poggio. 409-415
• Vicinal Risk MinimizationOlivier Chapelle, Jason Weston, Léon Bottou, Vladimir Vapnik. 416-422
• GaussianizationScott Saobing Chen, Ramesh A. Gopinath. 423-429
• The Missing Link - A Probabilistic Model of Document Content and Hypertext ConnectivityDavid A. Cohn, Thomas Hofmann. 430-436
• Improved Output Coding for Classification Using Continuous RelaxationKoby Crammer, Yoram Singer. 437-443
• Sparse Representation for Gaussian Process ModelsLehel Csató, Manfred Opper. 444-450
• Explaining Away in Weight SpacePeter Dayan, Sham Kakade. 451-457
• An Adaptive Metric Machine for Pattern ClassificationCarlotta Domeniconi, Jing Peng, Dimitrios Gunopulos. 458-464
• High-temperature Expansions for Learning Models of Nonnegative DataOliver B. Downs. 465-471
• Incorporating Second-Order Functional Knowledge for Better Option PricingCharles Dugas, Yoshua Bengio, François Bélisle, Claude Nadeau, René Garcia. 472-478
• Discovering Hidden Variables: A Structure-Based ApproachGal Elidan, Noam Lotner, Nir Friedman, Daphne Koller. 479-485
• Accumulator Networks: Suitors of Local Probability PropagationBrendan J. Frey, Anitha Kannan. 486-492
• Sequentially Fitting Inclusive Trees for Inference in Noisy-OR NetworksBrendan J. Frey, Relu Patrascu, Tommi Jaakkola, Jodi Moran. 493-499
• A New Approximate Maximal Margin Classification AlgorithmClaudio Gentile. 500-506
• Propagation Algorithms for Variational Bayesian LearningZoubin Ghahramani, Matthew J. Beal. 507-513
• The Kernel Gibbs SamplerThore Graepel, Ralf Herbrich. 514-520
• N-Body Problems in Statistical LearningAlexander G. Gray, Andrew W. Moore. 521-527
• Large Scale Bayes Point MachinesRalf Herbrich, Thore Graepel. 528-534
• Beyond Maximum Likelihood and Density Estimation: A Sample-Based Criterion for Unsupervised Learning of Complex ModelsSepp Hochreiter, Michael Mozer. 535-541
• Ensemble Learning and Linear Response Theory for ICAPedro A. d. F. R. Højen-Sørensen, Ole Winther, Lars Kai Hansen. 542-548
• Generalizable Singular Value Decomposition for Ill-posed DatasetsUlrik Kjems, Lars Kai Hansen, Stephen C. Strother. 549-555
• Algorithms for Non-negative Matrix FactorizationDaniel D. Lee, H. Sebastian Seung. 556-562
• Text Classification using String KernelsHuma Lodhi, John Shawe-Taylor, Nello Cristianini, Christopher J. C. H. Watkins. 563-569
• Constrained Independent Component AnalysisWei Lu, Jagath C. Rajapakse. 570-576
• Active Support Vector Machine ClassificationOlvi L. Mangasarian, David R. Musicant. 577-583
• The Unscented Particle FilterRudolph van der Merwe, Arnaud Doucet, Nando de Freitas, Eric A. Wan. 584-590
• A Mathematical Programming Approach to the Kernel Fisher AlgorithmSebastian Mika, Gunnar Rätsch, Klaus-Robert Müller. 591-597
• Automatic Choice of Dimensionality for PCAThomas P. Minka. 598-604
• On Iterative Krylov-Dogleg Trust-Region Steps for Solving Neural Networks Nonlinear Least Squares ProblemsEiji Mizutani, James Demmel. 605-611
• An Information Maximization Approach to Overcomplete and Recurrent RepresentationsOren Shriki, Haim Sompolinsky, Daniel D. Lee. 612-618
• Sparse Greedy Gaussian Process RegressionAlex J. Smola, Peter L. Bartlett. 619-625
• Kernel Expansions with Unlabeled ExamplesMartin Szummer, Tommi Jaakkola. 626-632
• Sparse Kernel Principal Component AnalysisMichael E. Tipping. 633-639
• Data Clustering by Markovian Relaxation and the Information Bottleneck MethodNaftali Tishby, Noam Slonim. 640-646
• Active Learning for Parameter Estimation in Bayesian NetworksSimon Tong, Daphne Koller. 647-653
• Mixtures of Gaussian ProcessesVolker Tresp. 654-660
• Tree-Based Modeling and Estimation of Gaussian Processes on Graphs with CyclesMartin J. Wainwright, Erik B. Sudderth, Alan S. Willsky. 661-667
• Feature Selection for SVMsJason Weston, Sayan Mukherjee, Olivier Chapelle, Massimiliano Pontil, Tomaso Poggio, Vladimir Vapnik. 668-674
• On a Connection between Kernel PCA and Metric Multidimensional ScalingChristopher K. I. Williams. 675-681
• Using the Nyström Method to Speed Up Kernel MachinesChristopher K. I. Williams, Matthias Seeger. 682-688
• Generalized Belief PropagationJonathan S. Yedidia, William T. Freeman, Yair Weiss. 689-695
• A Gradient-Based Boosting Algorithm for Regression ProblemsRichard S. Zemel, Toniann Pitassi. 696-702
• Regularized Winnow MethodsTong Zhang. 703-709
• A Silicon Primitive for Competitive LearningDavid Hsu, Miguel Figueroa, Chris Diorio. 713-719
• Smart Vision Chip Fabricated Using Three Dimensional Integration TechnologyHiroyuki Kurino, M. Nakagawa, Kang-Wook Lee, Tomonori Nakamura, Yuusuke Yamada, Ki Tae Park, Mitsumasa Koyanagi. 720-726
• Homeostasis in a Silicon Integrate and Fire NeuronShih-Chii Liu, Bradley A. Minch. 727-733
• Fast Training of Support Vector ClassifiersFernando Pérez-Cruz, Pedro Luis Alarcón-Diana, Angel Navia-Vázquez, Antonio Artés-Rodríguez. 734-740
• Four-legged Walking Gait Control Using a Neuromorphic Chip Interfaced to a Support Vector Learning AlgorithmSusanne Still, Bernhard Schölkopf, Klaus Hepp, Rodney J. Douglas. 741-747
• New Approaches Towards Robust, Adaptive Speech Recognition (invited paper)Hervé Bourlard, Samy Bengio, Katrin Weber. 751-757
• Speech Denoising and Dereverberation Using Probabilistic ModelsHagai Attias, John C. Platt, Alex Acero, Li Deng. 758-764
• Combining ICA and Top-Down Attention for Robust Speech RecognitionUn-Min Bae, Soo-Young Lee. 765-771
• Learning Joint Statistical Models for Audio-Visual Fusion and SegregationJohn W. Fisher III, Trevor Darrell, William T. Freeman, Paul A. Viola. 772-778
• Factored Semi-Tied Covariance MatricesMark J. F. Gales. 779-785
• Higher-Order Statistical Properties Arising from the Non-Stationarity of Natural SignalsLucas C. Parra, Clay Spence, Paul Sajda. 786-792
• One Microphone Source SeparationSam T. Roweis. 793-799
• Minimum Bayes Error Feature Selection for Continuous Speech RecognitionGeorge Saon, Mukund Padmanabhan. 800-806
• Periodic Component Analysis: An Eigenvalue Method for Representing Periodic Structure in SpeechLawrence K. Saul, Jont B. Allen. 807-813
• FaceSync: A Linear Operator for Measuring Synchronization of Video Facial Images and Audio TracksMalcolm Slaney, Michele Covell. 814-820
• Noise Suppression Based on Neurophysiologically-motivated SNR Estimation for Robust Speech RecognitionJürgen Tchorz, Michael Kleinschmidt, Birger Kollmeier. 821-827
• Shape Context: A New Descriptor for Shape Matching and Object RecognitionSerge Belongie, Jitendra Malik, Jan Puzicha. 831-837
• Emergence of Movement Sensitive Neurons Properties by Learning a Sparse Code for Natural Moving ImagesRafal Bogacz, Malcolm W. Brown, Christophe G. Giraud-Carrier. 838-844
• The Manhattan World Assumption: Regularities in Scene Statistics which Enable Bayesian InferenceJames M. Coughlan, Alan L. Yuille. 845-851
• Feature Correspondence: A Markov Chain Monte Carlo ApproachFrank Dellaert, Steven M. Seitz, Sebastian Thrun, Charles E. Thorpe. 852-858
• Keeping Flexible Active Contours on Track using Metropolis UpdatesTrausti T. Kristjansson, Brendan J. Frey. 859-865
• Color Opponency Constitutes a Sparse Representation for the Chromatic Structure of Natural ScenesTe-Won Lee, Thomas Wachtler, Terrence J. Sejnowski. 866-872
• Learning Segmentation by Random WalksMarina Meila, Jianbo Shi. 873-879
• Partially Observable SDE Models for Image Sequence Recognition TasksJavier R. Movellan, Paul Mineiro, Ruth J. Williams. 880-886
• Learning Sparse Image Codes using a Wavelet Pyramid ArchitectureBruno A. Olshausen, Phil Sallee, Michael S. Lewicki. 887-893
• Learning and Tracking Cyclic Human MotionDirk Ormoneit, Hedvig Sidenbladh, Michael J. Black, Trevor Hastie. 894-900
• Redundancy and Dimensionality Reduction in Sparse-Distributed Representations of Natural Objects in Terms of Their Local FeaturesPenio S. Penev. 901-907
• Rate-coded Restricted Boltzmann Machines for Face RecognitionYee Whye Teh, Geoffrey E. Hinton. 908-914
• Divisive and Subtractive Mask Effects: Linking Psychophysics and BiophysicsBarbara Zenger, Christof Koch. 915-921
• From Mixtures of Mixtures to Adaptive Transform CodingCynthia Archer, Todd K. Leen. 925-931
• A Neural Probabilistic Language ModelYoshua Bengio, Réjean Ducharme, Pascal Vincent. 932-938
• A Comparison of Image Processing Techniques for Visual Speech Recognition ApplicationsMichael S. Gray, Terrence J. Sejnowski, Javier R. Movellan. 939-945
• Support Vector Novelty Detection Applied to Jet Engine Vibration SpectraPaul Hayton, Bernhard Schölkopf, Lionel Tarassenko, Paul Anuzis. 946-952
• Recognizing Hand-written Digits Using Hierarchical Products of ExpertsGuy Mayraz, Geoffrey E. Hinton. 953-959
• Sex with Support Vector MachinesBaback Moghaddam, Ming-Hsuan Yang. 960-966
• Probabilistic Semantic Video IndexingMilind R. Naphade, Igor Kozintsev, Thomas S. Huang. 967-973
• Interactive Parts Model: An Application to Recognition of On-line Cursive ScriptPredrag Neskovic, Philip C. Davis, Leon N. Cooper. 974-980
• Learning Switching Linear Models of Human MotionVladimir Pavlovic, James M. Rehg, John MacCormick. 981-987
• Bayes Networks on Ice: Robotic Search for Antarctic MeteoritesLiam Pedersen, Dimitrios Apostolopoulos, William Whittaker. 988-994
• The Use of Classifiers in Sequential InferenceVasin Punyakanok, Dan Roth. 995-1001
• Machine Learning for Video-Based RenderingArno Schödl, Irfan A. Essa. 1002-1008
• Bayesian Video Shot SegmentationNuno Vasconcelos, Andrew Lippman. 1009-1015
• Programmable Reinforcement Learning AgentsDavid Andre, Stuart J. Russell. 1019-1025
• Exact Solutions to Time-Dependent MDPsJustin A. Boyan, Michael L. Littman. 1026-1032
• Decomposition of Reinforcement Learning for Admission Control of Self-Similar Call Arrival ProcessesJakob Carlström. 1033-1039
• Reinforcement Learning with Function Approximation Converges to a RegionGeoffrey J. Gordon. 1040-1046
• Hierarchical Memory-Based Reinforcement LearningNatalia Hernandez-Gardiol, Sridhar Mahadevan. 1047-1053
• Automated State Abstraction for Options using the U-Tree AlgorithmAnders Jonsson, Andrew G. Barto. 1054-1060
• Robust Reinforcement LearningJun Morimoto, Kenji Doya. 1061-1067
• Kernel-Based Reinforcement Learning in Average-Cost Problems: An Application to Optimal Portfolio ChoiceDirk Ormoneit, Peter W. Glynn. 1068-1074
• Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning TaskBrian Sallans, Geoffrey E. Hinton. 1075-1081
• Balancing Multiple Sources of Reward in Reinforcement LearningChristian R. Shelton. 1082-1088
• APRICODD: Approximate Policy Construction Using Decision DiagramsRobert St-Aubin, Jesse Hoey, Craig Boutilier. 1089-1095