FUNN 2 - A FUZZY NEURAL-NETWORK ARCHITECTURE FOR ADAPTIVE LEARNING AND KNOWLEDGE ACQUISITION/

Fuzzy neural networks have several features that make them well suited to a wide range of knowledge engineering applications. These strength s include fast and accurate learning, good generalization capabilities , excellent explanation facilities in the form of semantically meaning ful fuzzy rules, and the ability to accommodate both data and existing expert knowledge about the problem under consideration. This paper in vestigates adaptive learning, rule extraction and insertion, and neura l/fuzzy reasoning for a particular model of a fuzzy neural network cal led FuNN. As well as providing for representing a fuzzy system with an adaptable neural architecture, FuNN also incorporates a genetic algor ithm in one of its adaptation modes. A version of FuNN-FuNN/2, which e mploys triangular membership functions and correspondingly modified le arning and adaptation algorithms, is also presented in the paper. (C) Elsevier Science Inc. 1997.