Learning convergence of CMAC technique
Authors:
- Ching-Tsan ChiangCCChing-Tsan Chiang
- 1 November 1997
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 8 (6) , 1281-1292
Abstract
CMAC is one useful learning technique that was developed two decades ago but yet lacks adequate theoretical foundation. Most past studies focused on development of algorithms, improvement of the CMAC structure, and applications. Given a learning problem, very little about the CMAC learning behavior such as the convergence characteristics, effects of hash mapping, effects of memory size, the error bound, etc. can be analyzed or predicted. In this paper, we describe the CMAC technique with mathematical formulation and use the formulation to study the CMAC convergence properties. Both information retrieval and learning rules are described by algebraic equations in matrix form. Convergence characteristics and learning behaviors for the CMAC with and without hash mapping are investigated with the use of these equations and eigenvalues of some derived matrices. The formulation and results provide a foundation for further investigation of this technique.Keywords
This publication has 18 references indexed in Scilit:
- A comparison of five algorithms for the training of CMAC memories for learning control systemsAutomatica, 1992
- Controlling a truck with an adaptive critic CMAC designSIMULATION, 1992
- A pulsed neural network capable of universal approximationIEEE Transactions on Neural Networks, 1992
- Learning convergence in the cerebellar model articulation controllerIEEE Transactions on Neural Networks, 1992
- The CMAC and a theorem of KolmogorovNeural Networks, 1992
- CMAC-based adaptive critic self-learning controlIEEE Transactions on Neural Networks, 1991
- CMAC: an associative neural network alternative to backpropagationProceedings of the IEEE, 1990
- Real-time dynamic control of an industrial manipulator using a neural network-based learning controllerIEEE Transactions on Robotics and Automation, 1990
- Data Storage in the Cerebellar Model Articulation Controller (CMAC)Journal of Dynamic Systems, Measurement, and Control, 1975
- A New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)Journal of Dynamic Systems, Measurement, and Control, 1975