Fuzzy sets and neurocomputations: knowledge representation and processing in intelligent controllers

The problem of knowledge representation and processing for controllers for complex systems characterized by the availability of partial information is studied. Fundamental features of intelligent control are considered, and the role of fuzzy sets and neural nets is discussed. A new controller structure in which fuzzy sets and neural nets are used together is proposed, along with details of the associated design methodology. Learning processes in the resulting neural network are also clarified. All the formulas are given in detail.<
>