Abstract
This study attempts to develop a two-dimensional (2D) adaptive growing cerebellar model articulation controller network, which is constructed by connecting several 1D CMACs as a two-level tree structure. Without requiring the knowledge of the target function in advance, the number of states for each 1D CMAC as well as the number of CMACs is gradually increased during the adaptive growing process. Then the input space can be adaptively quantized by the proposed adaptive growing mechanism. In addition, the linear interpolation scheme is applied to calculate the network output and for simultaneously improving the learning performance and the generalization ability. Simulation results show that the proposed network not only has the adaptive quantization ability, but also can achieve a better learning accuracy with less memory requirement. Besides, the proposed network also could perform the best generalization ability among all considered models and, in general, attain a faster convergence speed.
This is a preview of subscription content, log in via an institution to check access.
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.: A new approach to manipulator control: The cerebellar model articulation controller (CMAC). J. Dyn. Syst. Meas. Contr. Trans. ASME 97(3), 220–227 (1975)
Albus, J.S.: Data storage in the cerebellar model articulation controller (CMAC). J. Dyn. Syst. Meas. Contr. Trans. ASME 97(3), 228–233 (1975)
Yeh, M.F.: Single-input CMAC control system. Neurocomputing 70, 2638–2644 (2007)
Glanz, F.H., Miller, W.T., Kraft, L.G.: An overview of the CMAC neural network. In: Proc. 1991 IEEE Neural Netw. Ocean Eng., pp. 301–308. IEEE Press, New York (1991)
Tao, T., Lu, H.C., Hung, T.H.: The CA-CMAC for downsampling image data size in the compressive domain. In: Proc. 2002 IEEE Int. Conf. Syst. Man Cybern., vol. 5. IEEE Press, New York (2002)
Lee, H.M., Chen, C.M., Lu, Y.F.: A self-organizing HCMAC neural-network classifier. IEEE Trans. Neural Netw. 14(1), 15–27 (2003)
Menozzi, A., Chow, M.Y.: On the training of a multi-resolution CMAC neural network. In: Proc. IEEE Int. Symp. Ind. Electron., vol. 3, pp. 1201–1205. IEEE Press, New York (1997)
Lane, S.H., Handelman, D.A., Gelfand, J.J.: Theory and development of higher-order CMAC neural networks. IEEE Contr. Syst. Mag. 12, 23–30 (1992)
Hung, S.L., Jan, J.C.: MS_CMAC neural-network learning model in structural engineering. J. Computing Civil Engrg., ASCE 13(1), 1–11 (1999)
Yeh, M.F., Chang, K.C.: Adaptive growing quantization for 1D CMAC network. In: Yu, W., He, H., Zhang, N. (eds.) ISNN 2009. LNCS, vol. 5551, pp. 118–127. Springer, Heidelberg (2009)
Horváth, G., Szabó, T.: Kernel CMAC with improved capability. IEEE Trans. Syst. Man Cybern. B 37(1), 124–138 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yeh, MF. (2010). Two-Dimensional Adaptive Growing CMAC Network. In: Zhang, L., Lu, BL., Kwok, J. (eds) Advances in Neural Networks - ISNN 2010. ISNN 2010. Lecture Notes in Computer Science, vol 6063. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13278-0_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-13278-0_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13277-3
Online ISBN: 978-3-642-13278-0
eBook Packages: Computer ScienceComputer Science (R0)