Introduction to the Theory of Neural Computation; Volume 1

Hertz, John; Krogh, Anders; Palmer, Richard G.

ISBN 10: 0201503956 / ISBN 13: 9780201503951

Published by Addison-Wesley Publishing Co, Redwood City, California, 1991

About this Item

Octavo in blue boards, 327 pp: illustrations; 25 cm. Lecture notes volume 1 | Contents: About the Santa Fe Institute , Santa Fe Institute Editorial Board September 1990 , Santa Fe Institute Studies in the Sciences of Complexity , Series Foreword , Foreword , Foreword , Preface , Introduction , The Hopfield Model , Extensions of the Hopfield Model , Optimization Problems , Simple Perceptrons , Multi-Layer Networks , Recurrent Networks , Unsupervised Hebbian Learning , Unsupervised Competitive Learning , Formal Statistical Mechanics of Neural Networks, Statistical Mechanics. Near fine(+); boards glossy; small stamp to free endpaper; pages crisp, bright, and clean; binding tight. First Edition (presumed; no prior editions or printings cited).

Seller Inventory # 106082

Bibliographic Details

• Title: Introduction to the Theory of Neural Computation; Volume 1
• Publisher: Addison-Wesley Publishing Co, Redwood City, California
• Publication Date: 1991
• Language: English
• ISBN 10: 0201503956
• ISBN 13: 9780201503951
• Binding: Hardcover
• Edition: 1st Edition
• Condition: Near fine(+)
• Seller catalogs:
  • English
  • Science, Technology & Computers

About this title

Synopsis

A clear exposition of the theoretical aspects of neural computation. No specific background other than mathematics (multi-variate calculus, differential equations, and linear algebra) is assumed. Annotation copyright Book News, Inc. Portland, Or.

Review

This book comprehensively discusses the neural network models from a statistical mechanics perspective. It starts with one of the most influential developments in the theory of neural networks: Hopfield's analysis of networks with symmetric connections using the spin system approach and using the notion of an energy function from physics. Introduction to the Theory of Neural Computation uses these powerful tools to analyze neural networks as associative memory stores and solvers of optimization problems. A detailed analysis of multi-layer networks and recurrent networks follow. The book ends with chapters on unsupervised learning and a formal treatment of the relationship between statistical mechanics and neural networks. Little information is provided about applications and implementations, and the treatment of the material reflects the background of the authors as physicists. However the book is essential for a solid understanding of the computational potential of neural networks. Introduction to the Theory of Neural Computation assumes that the reader is familiar with undergraduate level mathematics, but does not have any background in physics. All of the necessary tools are introduced in the book.