Unsupervised learning : foundations of neural computation / edited by Geoffrey Hinton and Terrence J. Sejnowski.

Format:

Book

Contributor:

Hinton, Geoffrey E.

Sejnowski, Terrence J. (Terrence Joseph)

Series:

Computational neuroscience

Language:

English

Subjects (All):

Learning--Physiological aspects.

Learning.

Neural networks (Computer science).

Learning--Computer simulation.

Neural computers.

Physical Description:

1 online resource (xvi, 398 pages) : illustrations.

Place of Publication:

Cambridge, Mass. : MIT Press, [1999]

System Details:

text file

Summary:

Since its founding in 1989 by Terrence Sejnowski, Neural Computation has become the leading journal in the field. "Foundations of Neural Computation"collects, by topic, the most significant papers that have appeared in the journal over the past nine years. This volume of "Foundations of Neural Computation," on unsupervised learning algorithms, focuses on neural network learning algorithms that do not require an explicit teacher. The goal of unsupervised learning is to extract an efficient internal representation of the statistical structure implicit in the inputs. These algorithms provide insights into the development of the cerebral cortex and implicit learning in humans. They are also of interest to engineers working in areas such as computer vision and speech recognition who seek efficient representations of raw input data.

Contents:

1 Unsupervised Learning / H. B. Barlow 1

2 Local Synaptic Learning Rules Suffice to Maximize Mutual Information in a Linear Network / Ralph Linsker 19

3 Convergent Algorithm for Sensory Receptive Field Development / Joseph J. Atick, A. Norman Redlich 31

4 Emergence of Position-Independent Detectors of Sense of Rotation and Dilation with Hebbian Learning: An Analysis / Kechen Zhang, Martin I. Sereno, Margaret E. Sereno 47

5 Learning Invariance from Transformation Sequences / Peter Foldiak 63

6 Learning Perceptually Salient Visual Parameters Using Spatiotemporal Smoothness Constraints / James V. Stone 71

7 What Is the Goal of Sensory Coding? / David J. Field 101

8 An Information-Maximization Approach to Blind Separation and Blind Deconvolution / Anthony J. Bell, Terrence J. Sejnowski 145

9 Natural Gradient Works Efficiently in Learning / Shun-ichi Amari 177

10 A Fast Fixed-Point Algorithm for Independent Component Analysis / Aapo Hyvarinen, Erkki Oja 203

11 Feature Extraction Using an Unsupervised Neural Network / Nathan Intrator 213

12 Learning Mixture Models of Spatial Coherence / Suzanna Becker, Geoffrey E. Hinton 223

13 Bayesian Self-Organization Driven by Prior Probability Distributions / Alan L. Yuille, Stelios M. Smirnaki, Lei Xu 235

14 Finding Minimum Entropy Codes / H. B. Barlow, T.P. Kaushal, G. J. Mitchison 249

15 Learning Population Codes by Minimizing Description Length / Richard S. Zemel, Geoffrey E. Hinton 261

16 The Helmholtz Machine / Peter Dayan, Geoffrey E. Hinton, Radford M. Neal, Richard S. Zemel 277

17 Factor Analysis Using Delta-Rule Wake-Sleep Learning / Radford M. Neal, Peter Dayan 293

18 Dimension Reduction by Local Principal Component Analysis / Nandakishore Kambhatla, Todd K. Leen 317

19 A Resource-Allocating Network for Function Interpolation / John Platt 341

20 Learning with Preknowledge: Clustering with Point and Graph Matching Distance Measures / Steven Gold, Anand Rangarajan, Eric Mjolsness 355

21 Learning to Generalize from Single Examples in the Dynamic Link Architecture / Wolfgang Konen, Christoph von der Malsburg 373.

Notes:

"A Bradford book."

OCLC-licensed vendor bibliographic record.

ISBN:

9780262288033

0262288036

0585358958

9780585358956

9780262338554

0262338556

OCLC:

47008258

Access Restriction:

Restricted for use by site license.