Theory and development of higher-order CMAC neural networks
- 1 April 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems
- Vol. 12 (2) , 23-30
- https://doi.org/10.1109/37.126849
Abstract
The cerebellar model articulation controller (CMAC) neural network is capable of learning nonlinear functions extremely quickly due to the local nature of its weight updating. The rectangular shape of CMAC receptive field functions, however, produces discontinuous (staircase) function approximations without inherent analytical derivatives. The ability to learn both functions and function derivatives is important for the development of many online adaptive filter, estimation, and control algorithms. It is shown that use of B-spline receptive field functions in conjunction with more general CMAC weight addressing schemes allows higher-order CMAC neural networks to be developed that can learn both functions and function derivatives. This also allows hierarchical and multilayer CMAC network architectures to be constructed that can be trained using standard error back-propagation learning techniques.Keywords
This publication has 15 references indexed in Scilit:
- Networks for approximation and learningProceedings of the IEEE, 1990
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- Sensory and motor maps in the mammalian superior colliculusTrends in Neurosciences, 1987
- Multidimensional Additive Spline ApproximationSIAM Journal on Scientific and Statistical Computing, 1983
- Universal classes of hash functionsJournal of Computer and System Sciences, 1979
- Tensor product approximations to data defined on rectangular meshes in N-spaceThe Computer Journal, 1976
- A New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)Journal of Dynamic Systems, Measurement, and Control, 1975
- Curve Fitting with Piecewise PolynomialsIMA Journal of Applied Mathematics, 1971
- Receptive fields, binocular interaction and functional architecture in the cat's visual cortexThe Journal of Physiology, 1962