Return to home page
Searching: Muskingum library catalog
  Previous Record Previous Item Next Item Next Record
  Reviews, Summaries, etc...
Author Reed, Russell D.
Title Neural smithing : supervised learning in feedforward artificial neural networks / Russell D. Reed and Robert J. Marks II.
Imprint Cambridge, Mass. : MIT Press, [1999]

View online
View online
Series Bradford book.
Subject Neural networks (Computer science)
Alt Name Marks, Robert J., II (Robert Jackson), 1950-
Description 1 online resource (viii, 346 pages) : illustrations
Note "A Bradford book."
Bibliography Note Includes bibliographical references (pages 319-338) and index.
Contents 1. Introduction -- 2. Supervised learning -- 3. Single-layer networks -- 4. MLP representational capabilities -- 5. Back-propagation -- 6. Learning rate and momentum -- 7. Weight-initialization techniques -- 8. The error surface -- 9. Faster variations of back-propagation -- 10. Classical optimization techniques -- 11. Genetic algorithms and neural networks -- 12. Constructive methods -- 13. Pruning algorithms -- 14. Factors influencing generalization -- 15. Generalization prediction and assessment -- 16. Heuristics for improving generalization -- 17. Effects of training with noisy inputs.
Summary "Artificial neural networks are nonlinear mapping systems whose structure is loosely based on principles observed in the nervous systems of humans and animals. The basic idea is that massive systems of simple units linked together in appropriate ways can generate many complex and interesting behaviors. This book focuses on the subset of feedforward artificial neural networks called multilayer perceptions (MLP). These are the most widely used neural networks, with applications as diverse as finance (forecasting), manufacturing (process control), and science (speech and image recognition)." "This book presents an extensive and practical overview of almost every aspect of MLP methodology, progressing from an initial discussion of what MLPs are and how they might be used to an in-depth examination of technical factors affecting performance. The book can be used as a tool kit by readers interested in applying networks to specific problems, yet it also presents theory and references outlining the last ten years of MLP research."--Jacket.
Note English.
Print version record.
ISBN 0585078386 (electronic bk.)
9780585078380 (electronic bk.)
9780262282215 (electronic bk.)
0262282216 (electronic bk.)
0262181908 (hc ; alk. paper)
9780262181907 (hc ; alk. paper)
OCLC # 42856076
Additional Format Print version: Reed, Russell D. Neural smithing. Cambridge, Mass. : MIT Press, ©1999 0262181908 (DLC) 98013416 (OCoLC)38468402
Table of Contents
2Supervised Learning7
3Single-Layer Networks15
4MLP Representational Capabilities31
6Learning Rate and Momentum71
7Weight-Initialization Techniques97
8The Error Surface113
9Faster Variations of Back-Propagation135
10Classical Optimization Techniques155
11Genetic Algorithms and Neural Networks185
12Constructive Methods197
13Pruning Algorithms219
14Factors Influencing Generalization239
15Generalization Prediction and Assessment257
16Heuristics for Improving Generalization265
17Effects of Training with Noisy Inputs277
ALinear Regression293
BPrincipal Components Analysis299
CJitter Calculations311
DSigmoid-like Nonlinear Functions315