Abstract
An improved neural networks online learning scheme is proposed to speed up the learning process in cerebellar model articulation controllers(CMAC). The improved learning approach is to use the learned times of the addressed hypercubes as the credibility (confidence) of the learned values in the early learning stage, and the updating data for addressed hypercubes is proportional to the inverse of the exponent of learned times, in the later stage the updating data for addressed hypercubes is proportional to the inverse of learned times. With this idea, the learning speed can indeed be improved.
This project is supported by the JiangSu Province Nature Science Foundation (BK 2004021)and the Key Project of Chinese Ministry of Education.( 105088).
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
Hinton, G.E., Mcclelland, J.L., Rumelhart, D.E.: Distributed representation. In: Rumelhart, et al. (eds.) Parallel Distributed Processing, vol. 3. MIT Press, Cambridge (1986)
Kosko, B.: A dynamical systems approach to machine intelligence, Neural Networks and Fuzzy Systems. Prentice-Hall, Englewood Cliffs (1992)
Albus, J.S.: A new approach to manipulator control: The cerebellar model articulation controller (CMAC). ASME J. Dynamic Systems, Measurement, Control, 220–227 (1975)
Albus, J.S.: Data storage in cerebellar model articulation controller (CMAC). ASME J. Dynamic Systems, Measurement, Control, 228–233 (1975)
Wong, Y.F., Sideris, A.: Learning convergence in cerebellar model articulation controller. IEEE Trans. Neural Networks 2, 115–121 (1992)
Lin, C.S., Chiang, C.T.: Learning convergence of CMAC technique. IEEE Trans. Neural Networks 6, 1281–1292 (1997)
Iiguni, Y.: Hierarchical image coding via cerebellar model arithmetic computers. IEEE Trans. Image Processing 6, 1393–1401 (1996)
Hong, C.M., Lin, C.H., Tao, T.: Grey-CMAC model. In: Proc. ISTED Int. Conf. High Technology Power Industry, pp. 39–44 (1997)
Nie, J., Linkens, D.A.: FCMAC: A fuzzified cerebellar model articulation controller with self-organizing capacity. Automatica 4, 655–664 (1994)
Geng, Z.J., Mccullough, C.L.: Missile control using fuzzy cerebellar model arithmetic computer neural networks, J. Guid., Control, Dyn. 3, 557–565 (1997)
Shun-Feng, S., Ted, T., Hung, T.H.: Credit assigned CMAC and its application to online learning robust controllers. IEEE Trans. on Systems, Man, and Cybernetics-—Part B: Cybernetics 2, 202–213 (2003)
Smalz, R., Conrad, M.: Combining evolution with credit apportionment: A new learning algorithm for neural nets. Neural Networks 2, 341–351 (1994)
Plantamura, V.L., Soucek, B., Visaggio, G.: Holographic fuzzy learning for credit scoring. In: Proc. Int. Joint Conf. Neural Networks, vol. 6, pp. 729–732 (1993)
Wang, Z.Q., Schiano, J.L., Ginsberg, M.: Hash-coding in CMAC neural networks. In: IEEE Int’l Conf. Neural Networks, pp. 1698–1703 (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
Zhu, D., Kong, M., Yang, Y. (2005). The Improved CMAC Model and Learning Result Analysis. In: Wang, L., Chen, K., Ong, Y.S. (eds) Advances in Natural Computation. ICNC 2005. Lecture Notes in Computer Science, vol 3610. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11539087_3
Download citation
DOI: https://doi.org/10.1007/11539087_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28323-2
Online ISBN: 978-3-540-31853-8
eBook Packages: Computer ScienceComputer Science (R0)