Title :
An overview of the CMAC neural network
Author :
Glanz, Filson H. ; Miller, W. Thomas ; Kraft, L. Gordon
Author_Institution :
Robotics Lab., New Hampshire Univ., Durham, NH, USA
Abstract :
The authors describe the cerebellar model arithmetic computer (CMAC) neural network, which is an alternative to backpropagated multilayer networks. CMAC has properties of generalization, rapid algorithmic computation based on least-mean-square (LMS) training, functional representation, output superposition, and practical hardware realization, all of which are discussed. Data concerning CMAC capacity and generalization are shown. Brief descriptions of applications in pattern recognition, robot control, and signal processing are given
Keywords :
neural nets; CMAC neural network; cerebellar model arithmetic computer; functional representation; generalization; least-mean-square; output superposition; rapid algorithmic computation; Application software; Computer networks; Digital arithmetic; Hardware; Least squares approximation; Multi-layer neural network; Neural networks; Pattern recognition; Quantum computing; Signal processing algorithms;
Conference_Titel :
Neural Networks for Ocean Engineering, 1991., IEEE Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-0205-2
DOI :
10.1109/ICNN.1991.163366
