Two Novel Learning Algorithms for CMAC Neural Network Based on Changeable Learning Rate
الموضوعات :Nazal Modhej 1 , Mohammad Teshnehlab 2 , Mashallah Abbasi Dezfouli 3
1 - Department of Computer Engineering,
Science and Research Branch, Islamic Azad University, Khouzestan.
2 - Khaje Nasir Toosi University of Technology
3 - Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Khouzestan
الکلمات المفتاحية: CMAC, Learning rate, Training iteration, Learning performance,
ملخص المقالة :
Cerebellar Model Articulation Controller Neural Network is a computational model of cerebellum which acts as a lookup table. The advantages of CMAC are fast learning convergence, and capability of mapping nonlinear functions due to its local generalization of weight updating, single structure and easy processing. In the training phase, the disadvantage of some CMAC models is unstable phenomenon or slower convergence speed due to larger fixed or smaller fixed learning rate respectively. The present research deals with offering two solutions for this problem. The original idea of the present research is using changeable learning rate at each state of training phase in the CMAC model. The first algorithm deals with a new learning rate based on reviation of learning rate. The second algorithm deals with number of training iteration and performance learning, with respect to this fact that error is compatible with inverse training time. Simulation results show that this algorithms have faster convergence and better performance in comparison to conventional CMAC model in all training cycles.
[1] J.S.Albus, "A New Approach to Manipulator Control: theCerebellar Model Articulation Controller(CMAC)," ASME J.Dynamics Systems, Measurment, Control, pp. 220-227, 19755.
[2] J.S. Albus, "Data Storage in the cerebellar Model Articulation Controller(CMAC)," ASME J.Dynamic Systems, Measurment, Control, pp. 228-233, 1975.
[3] Mato Baotic, Ivan Petrovic,Nedjeljko Peric,"Convex Optimizatio in Trainning of CMAC Neural Networks," Automation: Journal for control, Measurement, Electronics, Computing and Communicatios,Vol.42. No. 3-4,2001.
[4] Li Xin, Chen Wei, Chen Mei, Hefei,"Reinforcement Learning Controlbased on TWO-CMAC structure," in Conf. Rec. 2009 IEEE International Conference on Intelligent Human-Machine Systems and Cybernetics,pp. 116-121.
[5] PO-LUN CHANG, YING-KUEI YANG, HORNG-LIN SHIEH, "A novel learning framework of CMAC via Grey-area-time credit apportionment and Grey learning rate," in Conf. Rec. 2008 IEEE Proceedings of the Seventh International Conference on Machine Learning and Cybernetics, Kunmming, pp. 3096-3101.
[6] Luis Weuaga, "Active Training on the CMAC Neuarl Network," Neural Networks,2004. Proceedings. 2004 IEEE International Joint Conf. pp. 855-860. Vol. 2.
[7] Kamran Mohajeri, Ghasem Pishehvar, Mohammad Seifi,"CMAC Neural Networks Structure," in Conf. Rec. 2009 IEEE. Computer Intelligence in Robotics an Autonation (IRA), pp. 39-45.
[8] W. T. Miller, F. H. Glanz and L. G. Kraft, "CMAC: An Associative Neural Network Alternative to Backpropagation," Proceedings of the IEEE, Vol.78 ,No.10, pp. 1561-1567, 1990.
[9] S. H. Land, D. A. Handelman, and J. J. Gelfand, "Theory and development of higher-order CMAC neural networks," IEEE Control Syst. Mag., Vol. 12, no. 2, pp. 23-30, Apr. 1992.
[10] Francisco J. Gonzalez-Serrano, Anibal R. Figueiras-Vidal, and Antonio Artes-Rodiguez, "Generalizing CMAC Architecture and Training," IEEE Transactions on Neural Networks, vol. 9, no. 6, 1998.
[11] Ming-Feng Yeh and Kuang-Chiung Chang," A Self-Organizing CMAC Network With Gray Credit Assignment, IEEE Transactions on systems, man, and cybernetics part B:CYBERNETICS, vol. 36, no. 3, June 2006, pp. 623-635.
[12] M. F. Yeh and H. C. Lu, "On-LineAdaptive Quantization Input Space in CMAC Neural Network," IEEE International Conference on Systems, Man and Cybernetics, vol. 4, 2002.
[13] H.M. Lee and C. M. Chen, "Self-Organizing HCMAC Neural-Network classifier," IEEE Transaction on Neural Networks, vol.8, no.6, pp. 1281-1292, 1997.
[14] S. F. Su, T. Tao, and T. H. Hung, "Credit Assigned CMAC and its Application to Online Learning Robust Controllers," IEEE Transaction on System, Man, and Cybernetics-Part B: Cybernetics,vol. 33, no. 2, pp. 202-213, 2003.
[15] Luis Weruaga and Barbara Kieslinger, "Tikhonov Training of the CMAC Neural Networks, vol. 17, no. 3, pp. 613-622, 2006.
