Introduction

This introduction presents an overview of the key concepts discussed in the subsequent chapters of this book. The book discusses learning to denote machine learning based on the notion of change. It considers the theory and some applications of Stochastic Learning Automata, Artificial Neural Networks and Genetic/Evolutionary Algorithms. The book reviews the basic types of learning automata including discretised algorithms and relative reward strength algorithms and also discusses interconnected hierarchical automata and automata games. It deals with multilayer perceptrons, radial basis function networks, kohonen self-organisation networks, reinforcement learning neural networks, genetic algorithms, and the closely related evolutionary strategies and evolutionary programming. The book considers selected applications of the learning algorithms to problems in adaptive signal processing, control and communications. It describes the application of stochastic learning automata to parameter optimisation in adaptive filters. The book also considers a problem fundamental to both control and signal processing—identification of a non-linear system.