Expert System Using Hybridism among Symbolic and Connectionist Paradigms, Fuzzy Logic And, Genetic Algorithms

The Knowledge Acquisition (KA) process consists on extracting and representing knowledge of a domain expert. In this work, one of the goals is to minimize the intrinsic difficulties of the KA process. We have obtained all possible rules from the domain expert in a short time and also a set of examples. Other goal, we are proposed a Hybrid Expert System (HES) to minimize the problems of the KA task using a new methodology. Building this kind of hybrid architecture has led us to use many tools: symbolic paradigm, connectionist paradigm, fuzzy logic and, Genetic Algorithm (GA). Another aim goal of this paper is to present two new algorithms, e.g., the first one is a learning algorithm to be applied to fuzzy feed-forward neural networks, as well as complexity problems to optimize the network topology. The second one is for extracting fuzzy rules of a trained fuzzy neural network. The learning algorithm was inspired on the classical back-propagation algorithm. It owns some variations due to kind of network used. The extraction algorithm of fuzzy rules owns also some particularities. As the methodology developed to HES as both of algorithms were tested through toy and real problems.