Integration of Neural and Fuzzy

Abstract

In this chapter, the integration of neural networks and fuzzy systems will be discussed. A substantial portion of this material comes from reference [1]. The combination of the techniques of fuzzy logic systems and neural networks suggests the novel idea of transforming the burden of designing fuzzy logic control and decision systems to the training and learning of connectionist neural networks. This neuro-fuzzy and/or fuzzy-neural synergistic integration reaps the benefits of both neural networks and fuzzy logic systems. That is, the neural networks provide connectionist structure (fault tolerance and distributed representation properties) and learning abilities to the fuzzy logic systems, and the fuzzy logic systems provide the neural networks with a structural framework with high-level fuzzy IF-THEN rule thinking and reasoning. These benefits can be witnessed in three major integrated systems: neural fuzzy systems, fuzzy neural networks, and fuzzy neural hybrid systems. These three integrated systems, along with their applications, will be discussed and explored in the next six chapters, as well as in the Appendices.