ABSTRACT
Combining expert systems and artificial neural networks in a manner that exploits the strengths of both systems expands the applications to which either system could be applied individually. Fuzziness in expert systems more closely imitates the thinking and decision-making processes of humans. In this chapter, a method is given for converting a fuzzy rule-based expert system into a functionally equivalent artificial neural network. The approach used to translate any newly acquired knowledge back to the expert system is also provided. The knowledge base and inference engine of the expert system define the knowledge and processing of the neural network. Test results show that the neural network is able to effectively handle the fuzzy rule-base and that rules learned by the neural network can be successfully used by the expert system.
