Research Catalog

Title

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

Publication

Cambridge, Mass. : MIT Press, 1999.

Items in the Library & Off-site

Details

Additional Authors

• Hinton, Geoffrey E.
• Sejnowski, Terrence J. (Terrence Joseph)

Description

xvi, 398 p. : ill.; 23 cm.

Summary

• This volume, 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.

Series Statement

Computational neuroscience

Uniform Title

Computational neuroscience.

Subject

• Learning > Physiological aspects
• Neural circuitry
• Learning > Computer simulation
• Neural computers
• Nerve Net
• Learning
• Computer Simulation
• Neural Networks (Computer)

Note

• "A Bradford book."

Bibliography (note)

• Includes bibliographical references and index.

Contents

• 1. Unsupervised Learning / H. B. Barlow -- 2. Local Synaptic Learning Rules Suffice to Maximize Mutual Information in a Linear Network / Ralph Linsker -- 3. Convergent Algorithm for Sensory Receptive Field Development / Joseph J. Atick and A. Norman Redlich -- 4. Emergence of Position-Independent Detectors of Sense of Rotation and Dilation with Hebbian Learning: An Analysis / Kechen Zhang, Martin I. Sereno and Margaret E. Sereno -- 5. Learning Invariance from Transformation Sequences / Peter Foldiak -- 6. Learning Perceptually Salient Visual Parameters Using Spatiotemporal Smoothness Constraints / James V. Stone -- 7. What Is the Goal of Sensory Coding? / David J. Field -- 8. An Information-Maximization Approach to Blind Separation and Blind Deconvolution / Anthony J. Bell and Terrence J. Sejnowski -- 9. Natural Gradient Works Efficiently in Learning / Shun-ichi Amari -- 10. A Fast Fixed-Point Algorithm for Independent Component Analysis / Aapo Hyvdrinen and Erkki Oja --
• 11. Feature Extraction Using an Unsupervised Neural Network / Nathan Intrator -- 12. Learning Mixture Models of Spatial Coherence / Suzanna Becker and Geoffrey E. Hinton -- 13. Bayesian Self-Organization Driven by Prior Probability Distributions / Alan L. Yuille, Stelios M. Smirnakis and Lei Xu -- 14. Finding Minimum Entropy Codes / H. B. Barlow, T. P. Kaushal and G. J. Mitchison -- 15. Learning Population Codes by Minimizing Description Length / Richard S. Zemel and Geoffrey E. Hinton -- 16. The Helmholtz Machine / Peter Dayan, Geoffrey E. Hinton and Radford M. Neal / [et al.] -- 17. Factor Analysis Using Delta-Rule Wake-Sleep Learning / Radford M. Neal and Peter Dayan -- 18. Dimension Reduction by Local Principal Component Analysis / Nandakishore Kambhatla and Todd K. Leen -- 19. A Resource-Allocating Network for Function Interpolation / John Platt --
• 20. Learning with Preknowledge: Clustering with Point and Graph Matching Distance Measures / Steven Gold, Anand Rangarajan and Eric Mjolsness -- 21. Learning to Generalize from Single Examples in the Dynamic Link Architecture / Wolfgang Konen and Christoph von der Malsburg.

ISBN

026258168X (pbk. : alk. paper)

LCCN

98014784

OCLC

• 38550461
• ocm38550461
• SCSB-4785971

Owning Institutions

Columbia University Libraries