CMAC - AN ASSOCIATIVE NEURAL NETWORK ALTERNATIVE TO BACKPROPAGATION

The CMAC neural network, an alternative to backpropagated multilayer networks, is described. CMAC has the advantages of the following properties: local generalization, rapid algorithmic computation based on LMS training, incremental training, functional representation, output superposition, and a fast practical hardware realization, all of which are discussed. A geometrical explanation of how CMAC works is provided, and brief descriptions of applications in robot control, pattern recognition, and signal processing are given. Possible disadvantages of CMAC are that it does not have global generalization and that it can have noise due to hash coding. Care must be exercised, as with all neural networks, to assure that a low error solution will be learned. © 1990, IEEE