An Improved GGAPRBF Algorithm and Its Application to Function Approximation
LI Bin1, LAI XiaoPing2
1.Department of Mathematical and Physical Sciences, Shandong Institute of Light Industry, Jinan 250353 2.School of Information Engineering, Shandong University at Weihai, Weihai 264209
Abstract An improved learning algorithm for RBF neural network based on the GGAPRBF algorithm is proposed. The adaptive adjusting algorithm for the width of hidden neuron radial basis function and the dynamical regulation of overlap threshold are introduced into the GGAPRBF algorithm. The presented algorithm is compared with RAN, RANEKF, MRAN,IRAN and GGAPRBF(GAPRBF) algorithms by simulation on three benchmark problems in the function approximation area. The results indicate that the proposed algorithm provides good generalization performance with considerably reduction in network size and training time.
[1] Platt J. A ResourceAllocating Network for Function Interpolation. Neural Computation, 1991, 3(2): 213225 [2] Kadirkamanathan V, Niranjan M. A Function Estimation Approach to Sequential Learning with Neural Networks. Neural Computation, 1993, 5(6): 954975 [3] Lu Y W, Sunderararjan N, Saratchandran P. A Sequential Learning Scheme for Function Approximation Using Minimal Radial Basis Function Neural Networks. Neural Computation, 1997, 9(2): 461478 [4] Lai Xiaoping, Li Bin. An Efficient Learning Algorithm Generating Small RBF Neural Networks. Neural Network World, 2005, 15(6): 523533 [5] Huang Guangbin, Saratchandran P, Sundararajan N. An Efficient Sequential Learning Algorithm for Growing and Pruning RBF (GAPRBF) Networks. IEEE Trans on Systems, Man, and Cybernetics, 2004, 34(6): 22842292 [6] Huang Guangbin, Saratchandran P, Sundararajan N. A Generalized Growing and Pruning RBF (GGAPRBF) Neural Network for Function Approximation. IEEE Trans on Neural Networks, 2005, 16(1): 5767 [7] Yang Ge, Lü Jianhong, Liu Zhiyuan. A New Sequential Learning Algorithm for RBF Neural Networks. Science in China Series E: Engineering and Materials Science, 2004, 47(4): 447460 [8] Wang Ying, Huang Guangbin. SelfAdjustment of Neuron Impact Width in Growing and Pruning RBF (GAPRBF) Neuron Networks // Proc of the Joint Conference of the 4th International Conference on Information, Communications and Signal Processing. Singapore, Singapore: IEEE Press, 2003, Ⅱ: 10141017 [9] Li Bin. An Improvement of the RAN Learning Algorithm. Pattern Recognition and Artificial Intelligence,2006, 19(2): 220226 (in Chinese) (李 彬. 一种改进的RAN学习算法. 模式识别与人工智能, 2006, 19(2): 220226) [10] Li Y, Sundararajan N, Saratchandran P. Analysis of Minimal Radial Basis Function Network Algorithm for RealTime Identification of Nonlinear Dynamic Systems. IEE Proceedings: Control Theory and Applications, 2000, 147(4): 476484 [11] Blake C , Merz J. UCI Repository of Machine Learning Databases [DB/OL]. [20050415]. http://ics.uci.edu/~mlearn/MLRepository.html
2007, Vol. 20 
