Skip to Book Table of Contents
 
  Search the Book Contents
Enter words or phrases that might occur in the text. Tips
Search all books
Search only this Book
  Look Up Books You Know
Enter title words, author's name, publisher or ISBN. Tips
Purchase This Book Online
   
Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks
by Russell D. Reed and Robert J. Marks II ISBN: 0262181908
The MIT Press © 1999, 339 pages    
A practical approach to the application of multilayer perceptron neural networks to real-world problems.
 
Table of Contents Colleague Comments
Back Cover  

Synopsis  by Pete Loshin

How do you make a computer capable of making judgments based on sensory inputs? Instead of building a traditional computer, try emulating the brain. If you're comfortable with college level calculus and statistics as well as knowledgeable about neural networks and perceptrons, Neural Smithing can help. But don't expect any hand-holding: Reed and Marks concentrate on practical hints while staying clear of theoretical explanations. Despite a lack of exercises, this book reads like a graduate level textbook. The first chapters provide a bird's eye view of neural networks and supervised learning, but subsequent chapters quickly zero in on topics in supervised learning, in which systems are "adjusted" to accelerate the learning process. Later chapters discuss specific algorithms and methods, and many include "discussion" or "remarks" sections, containing comments and explanations about what approaches may be more successful than others.


Top of the page
Table of Contents
Neural Smithing - Supervised Learning in Feedforward Artificial Neural Networks
Preface
Chapter 1 - Introduction
Chapter 2 - Supervised Learning
Chapter 3 - Single-Layer Networks
Chapter 4 - MLP Representational Capabilities
Chapter 5 - Back-Propagation
Chapter 6 - Learning Rate and Momentum
Chapter 7 - Weight-Initialization Techniques
Chapter 8 - The Error Surface
Chapter 9 - Faster Variations of Back-Propagation
Chapter 10 - Classical Optimization Techniques
Chapter 11 - Genetic Algorithms and Neural Networks
Chapter 12 - Constructive Methods
Chapter 13 - Pruning Algorithms
Chapter 14 - Factors Influencing Generalization
Chapter 15 - Generalization Prediction and Assessment
Chapter 16 - Heuristics for Improving Generalization
Chapter 17 - Effects of Training with Noisy Inputs
Appendix A - Linear Regression
Appendix B - Principal Components Analysis
Appendix C - Jitter Calculations
Appendix D - Sigmoid-like Nonlinear Functions
Index
References
List of Figures
List of Tables
Top of the page
Back Cover

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.

About the Authors

Russell D. Reed is Research Assistant Professor of Electrical Engineering, and Robert J. Marks II is Professor of Electrical Engineering, both at the University of Washington.


Top of the page
Books24x7.com, Inc. © 1999-2001  –  Feedback