Abstract
CMAC (Cerebellar Model Articulation Controller) is a well-established computational model of the human cerebellum, and it has high speed learning ability. Actually, CMAC is used for learning of robot action. However, results obtained by learning are hard to understand for human because they are numeric data. The research on the skill acquisition of an operator by using Adaptive Learning CMAC (AL-CMAC) has been performed in our laboratory. In this research, the rule extraction method by Fuzzy Neural Network (FNN) from the learning result of AL-CMAC has been developed. In addition, an operator's skill is acquired from the operators whose a level of skill is different. By comparing the characteristic of expert's operation with that of amateur's one, we also extract an expert's particular skill.
