Neural smithing

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.

Table of contents

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
References
Index