Abstract
The CMAC neural network is by itself an adaptive processor. This paper studies the CMAC algorithm from the point of view of adaptive filter theory. Correspondingly, the correlation matrix is defined and the Wiener-Hopf equation is obtained for the CMAC neural network. It is revealed that the trace (i.e., sum of eigenvalues) of the correlation matrix is equal to the generalization parameter of the CMAC neural network. Using the tool of eigenanalysis, analytical bounds of the learning rate of CMAC neural network are derived which guarantee convergence of the weight vector in the mean. Moreover, a simple formula of estimating the misadjustment due to the gradient noise is derived.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Albus, J.S.: Theoretical and Experimental Aspects of a Cerebellar Model. Ph.D Dissertation. University of Maryland (1972)
Miller, W.T., Sutton, R.S., Werbos, P.J.: Neural Networks for Control. MIT Press, Cambridge (1990)
Miller, W.T., Glanz, F.H., Kraft, L.G.: CMAC: An Associative Neural Network Alternative to Backpropagation. In: Proceedings of the IEEE, Special Issue on Neural Networks, vol. II, pp. 1561–1567 (1990)
Lee, H.-M., Chen, V.-M., Lu, Y.-F.: A Self-organizing HCMAC Neural-Network Classifier. IEEE Trans. Neural Networks, 15–26 (2003)
Lin. C.-S., Chiang, C.-T.: Learning Convergence of CMAC Technique. IEEE Trans. Neural Networks, 1281–1292 (1997)
Miller, W.T.: Real Time Application of Neural Networks for Sensor-Based Control of Robots with Vision. IEEE SMC, 825–831 (1989)
Zhang, C., Canfield, J., Kraft, L.G., Kun, A.: A New Active Vibration Control Architecture Using CMAC Neural Networks. In: Proc. of 2003 IEEE ISIC, pp. 533–536 (2003)
Canfield, J., Kraft, L.G., Latham, P., Kun, A.: Filtered-X CMAC: An Efficient Algorithm for Active Disturbance Cancellation in Nonlinear Dynamical Systems. In: Proc. of 2003 IEEE ISIC, pp. 340–345 (2003)
Herold, D., Miller, W.T., Glanz, F.H., Kraft, L.G.: Pattern Recognition Using a CMAC Based Learning System. In: Proc. SPIE, Automated Inspection and High Speed Vision Architectures II, pp. 84–90 (1989)
Glanz, F.H., Miller, W.T.: Deconvolution and Nonlinear Inverse Filtering Using a CMAC Neural Network. In: Intl. Conf. on Acoustics and Signal Processing, pp. 2349–2352 (1989)
Haykin, S.: Adaptive Filter Theory, 3rd edn. Prentice-Hall, NJ (1996)
Widrow, B., Walach, E.: Adaptive Inverse Control, Englewood Cliffs. Prentice-Hall, NJ (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, C. (2005). Eigenanalysis of CMAC Neural Network. In: Wang, J., Liao, X., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3496. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427391_11
Download citation
DOI: https://doi.org/10.1007/11427391_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25912-1
Online ISBN: 978-3-540-32065-4
eBook Packages: Computer ScienceComputer Science (R0)