A Fuzzy CMAC Neural Network Model Based on Credit Assignment
Daqi Zhu, Min Kong · 2006
In order to improve online learning speed and accuracy of CMAC, a fuzzy CMAC neural network model based on credit assignment concept is designed. In the conventional CMAC and fuzzy CMAC learning scheme, the corrected amounts of errors are equally distributed into all addressed hypercubes, regardless of the credibility of those hypercubes values. The proposed improved learning approach is to use the learned times of the addressed hypercubes as the credibility (confidence) values of hypercubes learned, the corrected amounts of errors are proportion to the inversion of the learned times of the addressed hypercubes, With this idea, the learning speed demonstrated from examples can indeed become very fast.