Importance of membership functions: a comparative study on different learning methods for fuzzy inference systems

This paper investigates different adaptive structures for fuzzy inference systems. We examine the effect of membership functions on reasoning process when the number of rules is fixed. Three commonly used membership function shapes have been employed in this study. It has been shown that membership functions have the dominant effect on reasoning process rather than number of rules or inference mechanism. We compare our adaptive membership function scheme with two already proposed by others.<<ETX>>