## Advances in Neural Information Processing Systems 13: Proceedings of the 2000 ConferenceThe annual conference on Neural Information Processing Systems (NIPS) is the flagshipconference on neural computation. The conference is interdisciplinary, with contributions inalgorithms, learning theory, cognitive science, neuroscience, vision, speech and signal processing,reinforcement learning and control, implementations, and diverse applications. Only about 30 percentof the papers submitted are accepted for presentation at NIPS, so the quality is exceptionally high.These proceedings contain all of the papers that were presented at the 2000 conference. |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

Ranit AharonovBarki Isaac Meilijson and Eytan Ruppin | 10 |

HippocampallyDependent Consolidation in a Hierarchical Model ofNeocortex | 24 |

The Use of MDL to Select among Computational Models of Cognition | 38 |

The Early Word Catches the Weights | 52 |

Adaptive Object Representation with HierarchicallyDistributed Memory Sites | 66 |

Dendritic Compartmentalization Could Underlie Competition and Attentional | 82 |

Modelling Spatial Recall Mental Imagery and Neglect | 96 |

Stability and Noise in Biochemical Switches William Bialek | 103 |

Algorithms for Nonnegative Matrix Factorization | 556 |

Constrained Independent Component Analysis Wei Lu and Jagath C Rajapakse | 570 |

The Unscented Particle Filter | 584 |

Automatic Choice of Dimensionality for PCA Thomas P Minka | 598 |

An Information Maximization Approach to Overcomplete and Recurrent | 612 |

Kernel Expansions with Unlabeled Examples | 626 |

Data Clustering by Markovian Relaxation and the Information Bottleneck | 640 |

Mixtures of Gaussian Processes Volker Tresp | 654 |

A New Model of Spatial Representation in Multimodal Brain Areas | 117 |

Dopamine Bonuses Sham Kakade and Peter Dayan | 131 |

Processing of Time Series by Neural Circuits with Biologically Realistic Synaptic | 145 |

Universality and Individuality in a Neural Code Elad Schneidman | 159 |

Interfacing a Silicon Neuron to a Leech Heart | 173 |

Theory | 186 |

Competition and Arbors in Ocular Dominance Peter Dayan | 203 |

Permitted and Forbidden Sets in Symmetric ThresholdLinear Networks | 217 |

On Reversing Jensen s Inequality Tony Jebara and Alex Pentland | 231 |

Some New Bounds on the Generalization Error of Combined Classiﬁers | 245 |

Foundations for a Circuit Complexity Theory of Sensory Processing | 259 |

A Framework for Good | 273 |

Simulations With Field Theoretic Priors | 287 |

The Kernel Trick for Distances Bernhard Scholkopf | 301 |

Analysis of Bit Error Probability of DirectSequence CDMA Multiuser | 315 |

Algebraic Information Geometry for Learning Machines with Singularities | 329 |

Stagewise Processing in Errorcorrecting Codes and Image Restoration | 343 |

Convergence of Large Margin Separable Linear Classiﬁcation Tong Zhang | 357 |

A Variational MeanField Theory for Sigmoidal Belief Networks | 374 |

Model Complexity Goodness of Fit and Diminishing Returns | 388 |

A Linear Programming Approach to Novelty Detection | 395 |

Incremental and Decremental Support Vector Machine Learning | 409 |

Gaussianization Scott Saobing Chen and Ramesh A Gopinath | 423 |

Improved Output Coding for Classiﬁcation Using Continuous Relaxation | 437 |

Explaining Away in Weight Space Peter Dayan and Sham Kakade | 451 |

Hightemperature Expansions for Learning Models of Nonnegative Data | 465 |

A StructureBased Approach | 479 |

Sequentially Fitting Inclusive Trees for Inference in NoisyOR Networks | 493 |

Propagation Algorithms for Variational Bayesian Learning | 507 |

NBody Problems in Statistical Learning | 521 |

A SampleBased Criterion | 535 |

Ensemble Learning and Linear Response Theory for ICA | 542 |

Feature Selection for SVMs Jason Weston Sayan Mukherjee Olivier Chapelle | 668 |

Christopher K I Williams | 682 |

A GradientBased Boosting Algorithm for Regression Problems | 696 |

A Silicon Primitive for Competitive Learning | 713 |

Homeostasis in a Silicon Integrate and Fire Neuron | 727 |

Fourlegged Walking Gait Control Using a Neuromorphic Chip Interfaced to | 741 |

Speech Denoising and Dereverberation Using Probabilistic Models | 758 |

Learning Joint Statistical Models for Audio Visual Fusion and Segregation | 772 |

HigherOrder Statistical Properties Arising from the NonStationarity of Natural | 786 |

Minimum Bayes Error Feature Selection for Continuous Speech Recognition | 800 |

A Linear Operator for Measuring Synchronization of Video Facial | 814 |

Noise Suppression Based on Neurophysiologicallymotivated SNR Estimation | 821 |

Emergence of Movement Sensitive Neurons Properties by Learning a Sparse | 838 |

A Markov Chain Monte Carlo Approach | 852 |

Color Opponency Constitutes a Sparse Representation for the Chromatic | 866 |

Partially Observable SDE Models for Image Sequence Recognition Tasks | 880 |

Learning and Tracking Cyclic Human Motion | 894 |

Ratecoded Restricted Boltzmann Machines for Face Recognition | 908 |

From Mixtures of Mixtures to Adaptive Transform Coding | 925 |

A Comparison of Image Processing Techniques for Visual Speech Recognition | 939 |

Recognizing Handwritten Digits Using Hierarchical Products of Experts | 953 |

Probabilistic Semantic Video Indexing | 967 |

Learning Switching Linear Models of Human Motion | 981 |

The Use of Classiﬁers in Sequential Inference Vasin Punyakanok and Dan Roth | 995 |

Bayesian Video Shot Segmentation Nuno Vasconcelos and Andrew Lippman | 1009 |

Exact Solutions to TimeDependent MDPs Justin A Boyan and Michael L Littman | 1026 |

Reinforcement Learning with Function Approximation Converges to a Region | 1040 |

Automated State Abstraction for Options using the UTree Algorithm | 1054 |

Balancing Multiple Sources of Reward in Reinforcement Learning | 1082 |

Approximate Policy Construction Using Decision Diagrams | 1089 |

### Common terms and phrases

Advances in Neural analysis applied approach approximation basis functions Bayesian belief propagation Boltzmann machines bound cells classiﬁer clustering coefﬁcients complexity components convergence correlation corresponding covariance covariance matrix data set deﬁned deﬁnition denotes density dimensional distribution dynamics efﬁcient eigenvalues equation error estimate example feature space ﬁgure ﬁlter ﬁnd ﬁnding ﬁnite ﬁrst ﬁt ﬁxed frequency Gaussian processes hippocampus independent component analysis Information Processing Systems input iterative kernel kernel PCA layer learning algorithm linear Machine Learning margin matrix maximal method minimize mutual information Neural Information Processing neural networks neurons nodes noise nonlinear obtained optimal output parameters patterns perceptron performance pixels points posterior prediction prior probabilistic probability problem random representation sample sequence signal signiﬁcant solution speciﬁc speech spike statistical stimulus structure support vector machines synapses Theorem theory training set transform unsupervised learning update values variance visual weights