NEURAL-NETWORK-BASED FUZZY-LOGIC CONTROL AND DECISION SYSTEM

A general neural-network (connectionist) model for fuzzy logic control and decision/diagnosis systems is proposed. The proposed connectionist model can be contrasted with the traditional fuzzy logic control and decision system in their network structure and learning ability. Such fuzzy control/decision networks can be constructed from training examples by machine learning techniques, and the connectionist structure can be trained to develop fuzzy logic rules and find optimal input/output membership functions. By combining both unsupervised (self-organized) and supervised learning schemes, the learning speed converges much faster than the original backpropagation learning algorithm. This connectionist model also provides human-understandable meaning to the normal feedforward multilayer neural network in which the internal units are always opaque to the users. The connectionist structure also avoids the rule-matching time of the inference engine in the traditional fuzzy logic system. Two examples are presented to illustrate the performance and applicability of the proposed connectionist model.