Generalizing CMAC architecture and training
- 1 November 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 9 (6) , 1509-1514
Abstract
The cerebellar model articulation controller (CMAC) is a simple and fast neural-network based on local approximations. However, its rigid structure reduces its accuracy of approximation and speed of convergence with heterogeneous inputs. In this paper, we propose a generalized CMAC (GCMAC) network that considers different degrees of generalization for each input. Its representation abilities are analyzed, and a set of local relationships that the output function must satisfy are derived. An adaptive growing method of the network is also presented. The validity of our approach and methods are shown by some simulated examples.Keywords
This publication has 11 references indexed in Scilit:
- Fourier analysis of the generalized CMAC neural networkNeural Networks, 1998
- CMAC with General Basis FunctionsNeural Networks, 1996
- Hierarchical image coding via cerebellar model arithmetic computersIEEE Transactions on Image Processing, 1996
- The interpolation capabilities of the binary CMACNeural Networks, 1993
- A comparison of five algorithms for the training of CMAC memories for learning control systemsAutomatica, 1992
- The CMAC and a theorem of KolmogorovNeural Networks, 1992
- CMAC: an associative neural network alternative to backpropagationProceedings of the IEEE, 1990
- Integrating neural networks and knowledge-based systems for intelligent robotic controlIEEE Control Systems Magazine, 1990
- Sphere Packings, Lattices and Groups1988
- Mechanisms of planning and problem solving in the brainMathematical Biosciences, 1979