The Research on Flatness Pattern Recogniton Based on CMAC Neural Network

In traditional flat neural network, the topologic configurations are needed to be rebuilt with the width of cold strip changing. So that, the large learn assignment, slow convergence and local minimal in the network are observed. Moreover, the structure of the traditional neural network according to the experience has been proved that the model is time-consuming and complex. In this paper, a new approach of flatness pattern recognition is proposed based on the CMAC neural network. The difference of fuzzy distances between samples and the basic patterns is introduced as the inputs of the CMAC network. Simultaneity momentum term is imported to update the weight of this neural network. The new approach with the advantages, such as fast learning speed, good generalization, and easiness to implement, is efficient and intelligent. The simulation results show that the speed and accuracy of the flat pattern recognition model are improved obviously.