Neural and Adaptive Systems: Fundamentals Through Simulations

Table of Contents

Preface

Chapter 1 - Data Fitting with Linear Models

Chapter 1- Data Fitting with Linear Models

1.1 Introduction

1.2 Linear Models

1.3 Least Squares

1.4 Adaptive Linear Systems

1.5 Estimation of the Gradient The LMS Algorithm

1.6 A Methodology for Stable Adaptation

1.7 Regression for Multiple Variables

1.8 Newton's Method

1.9 Analytic versus Iterative Solutions

1.10 The Linear Regression Model

1.11 Conclusions

1.12 Exercises

1.13 NeuroSolutions Examples

1.14 Concept Map for Chapter 1

Chapters 2-11

Chapter 2 - Pattern Recognition

Chapter 3 - Multilayer Perceptrons

Chapter 4 - Designing and Training MLPs

Chapter 5 - Function Approximation with MLPs, RBFs, and Support Vector Machines

Chapter 6 - Hebbian Learning and Principal Component Analysis

Chapter 7 - Competitive and Kohonen Networks

Chapter 8 - Principles of Digital Signal Processing

Chapter 9 - Adaptive Filters

Chapter 10 - Temporal Processing with Neural Networks

Chapter 11 - Training and Using Recurrent Networks

Appendix A - Elements of Linear Algebra Pattern Recognition

appendixb

Appendix B - NeuroSolutions Tutorial

B.1 Introduction to NeuroSolutions

B.2 Introduction to the Interactive Examples

B.3 Basic Operation of NeuroSolutions

B.4 Probing the System

B.5 The Input Family

B.6 Training a Network

B.7 Summary