Fuzzy sets, fuzzy logic and the goals of artificial intelligence

Abstract

Summary form only given. Investigates some of the goals of artificial intelligence and the limitations of the purely symbolic approach. The integration of diverse theories can result in a more powerful approach to the study of intelligent systems. The use of fuzzy sets for knowledge representation, and of fuzzy logic for inference under uncertainty is illustrated. The advantage of combining fuzzy and neural network techniques is also discussed. A collection of new computing methods, globally known as soft computing, may lead us closer to the goals of artificial intelligence. The current fuzzy methodology must also be augmented. Fuzzy set theory, fuzzy logic, and associated techniques provide an excellent tool for interfacing the real world of measurements and the conceptual world embodied by language. We discuss the tradeoff in accuracy versus flexibility and we argue that when immediate, practical results are of primary concern the usual desire for accuracy and formal treatment decreases. >