Unsupervised Learning Neural Networks

Abstract

This chapter introduces the basic concepts and notation of unsupervised learning neural networks. Unsupervised networks are useful for analyzing data without having the desired outputs; in this case, the neural networks evolve to capture density characteristics of a data phase. We will describe in some detail competitive learning networks, Kohonen self-organizing networks, learning vector quantization, and Hopfield networks. We will also show some examples of these networks to illustrate their possible application in solving real-world problems in pattern recognition.