ENHANCING NEURAL CONTROL-SYSTEMS BY FUZZY-LOGIC AND EVOLUTIONARY REINFORCEMENT

Neural networks are widely used for system modelling and control becau se of their ability to approximate complex non-linear functions. Fuzzy systems, similarly, have been shown to be able to approximate or mode l any nonlinear system. Fuzzy-logic and neural systems, however, have very contrasting application requirements and it has been said that th eir integration offers a facility to bridge symbolic knowledge process ing and connectionist learning. The significance of the integration be comes more apparent by considering their disparities. Neural networks do not provide a strong scheme for knowledge representation, while fuz zy systems do not possess capabilities for automated learning. On the other hand another learning method has emerged recently, as an alterna tive to inductive techniques used with neural networks, namely, geneti c or evolutionary learning. This paper will present a technique for th e fusion of the three paradigms in a learning control context. It will describe a type of learning, known as Evolutionary Algorithm Reinforc ement Learning (EARL), which is used to optimise a fuzzy neural contro l system. Art application case study is also presented.