Implementation of Fuzzy Inference Systems Using Neural Network Techniques

Fuzzy inference systems work well in many control applications. One drawback, however, is determining membership functions and inference control rules required to implement the system, which are usually supplied by experts. One alternative is to use a neural network-type architecture to implement the fuzzy inference system, and neural network-type training techniques to learn the control parameters needed by the fuzzy inference system. By using a generalized version of a neural network, the rules of the fuzzy inference system can be learned without the assistance of experts.