Supervised Learning Neural Networks

Abstract

In this chapter, we describe the basic concepts, notation, and basic learning algorithms for supervised neural networks that will be of great use for solving pattern recognition problems in the following chapters of this book. The chapter is organized as follows: backpropagation for feedforward networks, radial basis networks, adaptive neuro-fuzzy inference systems (ANFIS) and applications. First, we give a brief review of the basic concepts of neural networks and the basic backpropagation learning algorithm. Second, we give a brief description of the momentum and adaptive momentum learning algorithms. Third, we give a brief review of the radial basis neural networks. Finally, we end the chapter with a description of the adaptive neuro-fuzzy inference system (ANFIS) methodology. We consider this material necessary to understand the new methods for pattern recognition that will be presented in the final chapters of this book.