ANN Rule Extraction using Evolutionary Programmed Fuzzy Membership Functions

Abstract

An algorithm is presented that uses evolutionary programming to construct fuzzy membership functions that are used to extract Zadeh-Mamdani fuzzy rules from a constructive neural network. The algorithm has potential applications in fields such as data mining and knowledge-based decision support systems. Evaluation of the algorithm over two well known benchmark data sets shows that while the results are promising, some problems are apparent. These problems provide avenues for further research.