Author(s)

S.G. Tzafestas & G.B. Stamou

Abstract

Fuzzy systems and neural systems belong to the class of model free estimators and possess a high degree of parallelism. Due to these features several investigators have tried to produce several models of neuro-fuzzy inference systems with combined properties. The purpose of the present paper is to extend and improve one of these neuro-fuzzy structures such that to obtain better inferences. The system is based on the Keller-Yager-Tahani (K-Y-T) neuro-fuzzy model and uses Hamacher's intersection function /#(a,6) or Sugeno's complement function c^(a). The operation of the system is briefly described and it's features are established fn the form of four theorems. The capabilities of the system are

Keywords