APPROXIMATE CASE-BASED REASONING ON NEURAL NETWORKS

In this paper, based on the deeper analysis of the features of fuzzy l ogic and approximate reasoning, the concept of approximate case-based reasoning (ACBR) is introduced. According to the inference mechanism o f ACBR, an implementation on neural networks is proposed. Mapping the implication relation between the premise(s) and the consequence of a f uzzy rule to the weight of a corresponding neural network unit, an app roximate case-based reasoning on neural networks can be realized. The self-organizing and self-learning procedure can be executed by modifyi ng the weight.