LEARNING FUZZY RULES AND APPROXIMATE REASONING IN FUZZY NEURAL NETWORKS AND HYBRID SYSTEMS

The paper considers both knowledge acquisition and knowledge interpret ation tasks as tightly connected and continuously interacting processe s in a contemporary knowledge engineering system. Fuzzy rules are used here as a framework for knowledge representation. An algorithm REFuNN for fuzzy rules extraction from adaptive fuzzy neural networks (FuNN) is proposed. A case study of Iris classification is chosen to illustr ate the algorithm. Interpretation of fuzzy rules is possible by using fuzzy neural networks or by using standard fuzzy inference methods. Bo th approaches are compared in the paper based on the case example. A h ybrid environment FuzzyCOPE which facilitates neural network simulatio n, fuzzy rules extraction from fuzzy neural networks and fuzzy rules i nterpretation by using different methods for approximate reasoning is briefly described.