Fuzzy systems and neural networks have attracted the growing interest of researchers, scientists, engineers, practitioners, and students in various scientific and engineering areas. Fuzzy sets and fuzzy logic are based on the way the brain deals with inexact information, while neural networks (or artificial neural networks) are modeled after the physical architecture of the brain. Although the fundamental inspirations for these two fields are quite different, there are a number of parallels that point out their similarities, The intriguing differences and similarities between these two fields have prompted the writing of this book to examine the basic concepts of fuzzy set theory, fuzzy logic, fuzzy logic control systems, and neural networks; to explore their applications separately and in combination; and to explore the synergism of integrating these two techniques for the realization of intelligent systems for various applications.

Since the publication of Lotfi Zadeh's seminal work, "Fuzzy Sets," in 1965, the number and variety of applications of fuzzy logic have been growing. The performance of fuzzy logic control and decisión systems critically depends On the input and output membership functions, the fuzzy logic control rules, and the fuzzy inference mechanism. Although a great amount of literature has been published dealing with the applications and the theoret- ¿cal issues of fuzzy logic control and decisión systems, a unified and systematic design methodology has yet to be developed. The use of neural networks to automate and synthesize the design of a general fuzzy logic control or decisión system presents a novel and innovative approach and a viable design solution to this difficult design and realization problem.