Analogue imprecision in MLP training / Peter J. Edwards, Alan F. Murray.

Format:

Book

Author/Creator:

Edwards, Peter J. (Peter John)

Contributor:

Murray, Alan F.

Series:

Progress in neural processing ; 4.

Progress in neural processing ; 4

Language:

English

Subjects (All):

Neural networks (Computer science).

Perceptrons.

Physical Description:

xi, 178 pages : illustrations ; 23 cm.

Place of Publication:

Singapore ; River Edge, NJ : World Scientific, [1996]

Summary:

Hardware inaccuracy and imprecision are important considerations when implementing neural algorithms. This book presents a study of synaptic weight noise as a typical fault model for analogue VLSI realisations of MLP neural networks and examines the implications for learning and network performance. The aim of the book is to present a study of how including an imprecision model into a learning scheme as a"fault tolerance hint" can aid understanding of accuracy and precision requirements for a particular implementation. In addition the study shows how such a scheme can give rise to significant performance enhancement.

Notes:

Includes bibliographical references (pages 165-172) and index.

ISBN:

9810227396

OCLC:

34710796