Advances in Neural Information Processing Systems: Proceedings of the 2001 Conference, Nide 14,Numerot 1–2Thomas G. Dietterich, Suzanna Becker, Professor of Information Engineering Zoubin Ghahramani, Zoubin Ghahramani MIT Press, 2002 - 1600 sivua The proceedings of the 2001 Neural Information Processing Systems (NIPS) Conference. The annual conference on Neural Information Processing Systems (NIPS) is the flagship conference on neural computation. The conference is interdisciplinary, with contributions in algorithms, learning theory, cognitive science, neuroscience, vision, speech and signal processing, reinforcement learning and control, implementations, and diverse applications. Only about 30 percent of 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 2001 conference. |
Kirjan sisältä
Tulokset 1 - 5 kokonaismäärästä 80
Valitettavasti tämän sivun sisältö on rajoitettu.
Valitettavasti tämän sivun sisältö on rajoitettu.
Valitettavasti tämän sivun sisältö on rajoitettu.
Valitettavasti tämän sivun sisältö on rajoitettu.
Valitettavasti tämän sivun sisältö on rajoitettu.
Sisältö
Modeling Temporal Structure in Classical Conditioning | 3 |
Motivated Reinforcement Learning | 11 |
Human Data and a Model | 19 |
Fragment Completion in Humans and Machines | 27 |
Natural Language Grammar Induction using a ConstituentContext Model | 35 |
The Emergence of Multiple Movement Units in the Presence of Noise and Feedback Delay | 43 |
A Rational Analysis of Cognitive Control in a Speeded Discrimination Task | 51 |
A Bayesian Model Predicts Human Parse Preference and Reading Times in Sentence Processing | 59 |
Novel Iteration Schemes for the Cluster Variation Method | 415 |
Efficiency versus Convergence of Boolean Kernels for OnLine Learning Algorithms | 423 |
SmallWorld Phenomena and the Dynamics of Information | 431 |
Kernel Machines and Boolean Functions | 439 |
Boosting and Maximum Likelihood for Exponential Models | 447 |
Means Correlations and Bounds | 455 |
A Variational Approach to Learning Curves | 463 |
Entropy and Inference Revisited | 471 |
Grammar Transfer in a Second Order Recurrent Neural Network | 67 |
Generalizable Relational Binding from Coarsecoded Distributed Representations | 75 |
Generalization and Binding | 83 |
Grammatical Bigrams | 91 |
Causal Categorization with Bayes Nets | 99 |
Constructing Distributed Representations using Additive Clustering | 107 |
Reinforcement Learning and Time Perceptiona Model of Animal Experiments | 115 |
A Quantitative Model of Counterfactual Reasoning | 123 |
Bayesian Morphometry of Hippocampal Cells Suggests SameCell Somatodendritic Repulsion | 133 |
Modularity in the Motor System Decomposition of Muscle Patterns as Combinations of TimeVarying Synergies | 141 |
Receptive Field Structure of Flow Detectors for Heading Perception | 149 |
Towards Brain Computer Interfacing | 157 |
Orientational and Geometric Determinants of Place and Headdirection | 165 |
Group Redundancy Measures Reveal Redundancy Reduction in the Auditory Pathway | 173 |
A MaximumLikelihood Approach to Modeling Multisensory Enhancement | 181 |
ACh Uncertainty and Cortical Inference | 189 |
Learning in an Unlearnable Force Field | 197 |
Exact Differential Equation Population Dynamics for IntegrateandFire Neurons | 205 |
Probabilistic Inference of Hand Motion from Neural Activity in Motor Cortex | 213 |
A Theory of Neural Integration in the HeadDirection System | 221 |
3 State Neurons for Contextual Processing | 229 |
Associative Memory in Realistic Neuronal Networks | 237 |
Selfregulation Mechanism of Temporally Asymmetric Hebbian Plasticity | 245 |
InformationGeometric Decomposition in Spike Analysis | 253 |
Eye Movements and the Maturation of Cortical Orientation Selectivity | 261 |
Characterizing Neural Gain Control using Spiketriggered Covariance | 269 |
Correlation Codes in Neuronal Populations | 277 |
Why Neuronal Dynamics should Control Synaptic Learning Rules | 285 |
Effective Size of Receptive Fields of Inferior Temporal Visual Cortex Neurons in Natural Scenes | 293 |
Activity Driven Adaptive Stochastic Resonance | 301 |
Spike Timing and the Coding of Naturalistic Sounds in a Central Auditory Area of Song Birds | 309 |
Neural Implementation of Bayesian Inference in Population Codes | 317 |
Generating Velocity Tuning by Asymmetric Recurrent Connections | 325 |
Sampling Techniques for Kernel Methods | 335 |
Geometrical Singularities in the Neuromanifold of Multilayer Perceptrons | 343 |
The Noisy Euclidean Traveling Salesman Problem and Learning | 351 |
On the Generalization Ability of OnLine Learning Algorithms | 359 |
On KernelTarget Alignment | 367 |
PAC Generalization Bounds for Cotraining | 375 |
Analysis of Sparse Bayesian Learning | 383 |
Algorithmic Luckiness | 391 |
Distribution of Mutual Information | 399 |
Information Geometrical Framework for Analyzing Belief Propagation Decoder | 407 |
Asymptotic Universality for Learning Curves of Support Vector Machines | 479 |
On the Convergence of Leveraging | 487 |
Scaling Laws and Local Minima in Hebbian ICA | 495 |
Computing Time Lower Bounds for Recurrent Sigmoidal Neural Networks | 503 |
On the Concentration of Spectral Properties | 511 |
Gaussian Process Regression with Mismatched Models | 519 |
InformationGeometrical Significance of Sparsity in Gallager Codes | 527 |
Fast Parameter Estimation Using Greens Functions | 535 |
Generalization Performance of Some Learning Problems in Hilbert Functional Spaces | 543 |
SemiSupervised MarginBoost | 553 |
RaoBlackwellised Particle Filtering via Data Augmentation | 561 |
Thin Junction Trees | 569 |
The Infinite Hidden Markov Model | 577 |
Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering | 585 |
Duality Geometry and Support Vector Regression | 593 |
Latent Dirichlet Allocation | 601 |
Incorporating Invariances in NonLinear Support Vector Machines | 609 |
A Generalization of Principal Component Analysis to the Exponential Family | 617 |
Convolution Kernels for Natural Language | 625 |
A Parallel Mixture of SVMs for Very Large Scale Problems | 633 |
Pranking with Ranking | 641 |
Spectral Kernel Methods for Clustering | 649 |
TAP Gibbs Free Energy Belief Propagation and Sparsity | 657 |
Adaptive Nearest Neighbor Classification using Support Vector Machines | 665 |
Learning from Infinite Data in Finite Time | 673 |
A Kernel Method for MultiLabelled Classification | 681 |
Approximate Dynamic Programming via Linear Programming | 689 |
Adaptive Sparseness Using Jeffreys Prior | 697 |
Incremental Learning and Selective Sampling via Parametric Optimization Framework for SVM | 705 |
Adaptive Particle Filters | 713 |
Fast LargeScale TransformationInvariant Clustering | 721 |
Learning to Model Observations as Products of Hidden Variables | 729 |
Very Loopy Probability Propagation for Unwrapping Phase Images | 737 |
Discriminative Direction for Kernel Classifiers | 745 |
Escaping the Convex Hull with Extrapolated Vector Machines | 753 |
Kernel Feature Spaces and Nonlinear Blind Source Separation | 761 |
The Method of Quantum Clustering | 769 |
Active Information Retrieval | 777 |
Online Learning with Kernels | 785 |
A Dynamic HMM for Online Segmentation of Sequential Data | 793 |
Minimax Probability Machine | 801 |
809 | |
Muita painoksia - Näytä kaikki
Advances in Neural Information Processing Systems ..., Nide 14,Numerot 1–2 Thomas G. Dietterich,Suzanna Becker Esikatselu ei käytettävissä - 2002 |