NEURAL NETWORKS FOR PATTERN RECOGNITION by Christopher M. Bishop ( 9780198538646 )

Item Details

Title:

NEURAL NETWORKS FOR PATTERN RECOGNITION

By:

Christopher M. Bishop

Format:

Paperback

List price:

£91.00

Our price:

£79.63

Discount:

12.5% off

You save:

£11.37

ISBN 10:

0198538642

ISBN 13:

9780198538646

Availability:

Usually dispatched within 3-5 days.

Delivery rates

Stock:

Currently 2 available

Publisher:

OXFORD UNIVERSITY PRESS

Pub. date:

23 November, 1995

Pages:

504

Description:

This book is the first to provide a comprehensive account of neural networks from a statistical perspective. Its emphasis is on pattern recognition, which currently represents the area of greatest applicability for neural networks. By focusing on pattern recognition, the book provides a much more extensive treatment of many topics than is available in earlier books.

Synopsis:

This book provides the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition. After introducing the basic concepts of pattern recognition, the book describes techniques for modelling probability density functions, and discusses the properties and relative merits of the multi-layer perceptron and radial basis function network models. It also motivates the use of various forms of error functions, and reviews the principal algorithms for error function minimization. As well as providing a detailed discussion of learning and generalization in neural networks, the book also covers the important topics of data processing, feature extraction, and prior knowledge. The book concludes with an extensive treatment of Bayesian techniques and their applications to neural networks.

Illustrations:

line figures

Publication:

Imprint:

Clarendon Press

Returns:

Returnable

Some other items by this author:

AMERICAN EXAMPLES

CONNECTIONIST SYMBOL PROCESSING (PB)

DEEP LEARNING

NEURAL NETWORKS AND MACHINE LEARNING (HB)