A New CMAC Neural Network Model with Adaptive Quantization Input Layer

摘要

In this paper, we first discuss the structure, principle and learning algorithm of CMAC neural network model. A new adaptive quantization method based on competitive learning is then proposed to quantimize the inputs of CMAC according to the degree of variations of the approximated function. Theoretical analysis and simulation results show that with the input layer using this algorithm CMAC can approximate more accurately and efficiently than the original model using equal-size quantization method.