A balanced learning CMAC neural networks model and its application to identification

In this paper, a concept of balanced learning is presented, and an improved neural networks learning scheme is proposed to speed up the learning process in cerebellar model articulation controllers (CMAC). In the conventional CMAC learning scheme, the corrected amounts of errors are equally distributed into all addressed hypercubes, regardless of the credibility of those hypercubes. The proposed improved learning approach is to use the inversion of the kthpower of learned times of addressed hypercubes as the credibility, the learning speed is different at different k. For every situation it can be found a optimal learning parameter k. To demonstrate the online learning capability of the proposed balanced learning CMAC scheme, two nonlinear system identification example are given.