Abstract
This paper deals with the problem of adaptation of radial basis function neural networks (RBF NN). A new RBF NN supervised training algorithm is proposed. This method possesses the distinctive properties of Lyapunov Theory-based Adaptive Filtering (LAF) in [1]-[2]. The method is different from many RBF NN training using gradient search methods. A new Lyapunov function of the error between the desired output and the RBF NN output is first defined. The output asymptotically converges to the desired output by designing the adaptation law in Lyapunov sense. Error convergence analysis in this paper has proven that the design of the new RBF NN training algorithm is independent of statistic properties of input and output signals. The new adaptation law has better tracking capability compared with the tracking performance of LAF in [1]-[2]. The performance of the proposed technique is illustrated through the adaptive prediction of nonlinear and nonstationary speech signals.
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.
Similar content being viewed by others
References
Phooi, S.K., Man, Z., Wu, H.R.: Lyapunov Theory-based Radial Basis Function Networks for Adaptive Filtering. IEEE Transaction on Circuit and System 1 49(8), 1215–1221 (2002)
ZhiHong, M., Wu, H.R., Lai, W., Nguyen, T.: Design of Adaptive Filters Using Lyapunov Stability Theory. In: The 6th IEEE International Workshop on Intelligent Signal Processing and Communication Systems, pp. 304–308 (1998)
Haykin, S.: Neural Network: A Comprehensive Foundation. Macmillan, New York (1994)
Chen, T., Chen, H.: Approximation capability to functions of several variables, nonlinear functionals, and operators by radial basis function neural networks. IEEE Trans. Neural Networks 6, 904–910 (1995)
Broomhead, D.S., Lowe, D.: Multivariable functional interpolation and adaptive networks. Complex Systems 2, 321–355 (1988)
Moody, J.E., Darken, C.J.: Fast learning in networks of locally-tuned processing units. Neural Comput. 1, 281–294 (1989)
Karayiannis, N.B., Mi, W.: Growing radial basis neural networks: Merging supervised and unsupervised learning with network growth techniques. IEEE Trans. Neural Networks 8, 1492–1506 (1997)
Poggio, T., Girosi, F.: Regularization algorithms for learning that are equivalent to multilayer networks. Science 247, 978–982 (1990)
Chen, S., Cowan, C.F.N., Grant, P.M.: Orthogonal least squares learning algorithm for radial basis function networks. IEEE Trans.Neural Networks 2, 302–309 (1991)
Cha, I., Kassam, S.A.: Interference cancellation using radial basis function networks. Signal Processing 47, 247–268 (1995)
Dinz, P.S.R.: Adaptive filtering: algorithms and practical implementation. Kluwer Academic Publishers, Boston, MA (1997)
Treichler, J.R., Johnson, C.R., Larimore, M.G.: The theory and design of adaptive filters. Prentice Hall, Englewood Cliffs (2001)
Alexandridis, A., Haralambos, S., George, B.: A new algorithm for online structure and parameter adaptation of RBF networks. Neural Networks 16, 1003–1017 (2003)
Fung, C.F., Billings, S.A., Luo, W.: Online supervised adaptive training using radial basis function networks. Neural Networks, 9(9), 1597–1617
Zheng, G.L., Billings, S.A.: Radial basis function network configuration using mutual information and orthogonal least squares algorithm. Neural Networks, 9(9), 1619–1673
Slotine, J-J.E., Li, W.: Applied nonlinear control. Prentice-Hall, Englewood Cliffs, NJ (1991)
Haykin, S.: Adaptive filtering theory. Prentice-Hall, Englewood Cliffs, NJ (1985)
Haykin, S.: Nonlinear Adaptive Prediction of Nonstationary Signals. IEEE Trans. Signal Processing, 43(2) (February 1995)
Yee, P., Haykin, S.: A dynamic regularized RBF networks for nonlinear, nonstationary time series prediction, IEEE Trans. Signal Processing, 47(9) (1999)
Baltersee, J., Jonathon, A.: Nonlinear adaptive prediction of speech with a pipelined recurrent neural network. IEEE Trans. Signal Processing, 46(8) (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Phooi, S.K., L.M, A. (2007). New Radial Basis Function Neural Network Training for Nonlinear and Nonstationary Signals. In: Wang, Y., Cheung, Ym., Liu, H. (eds) Computational Intelligence and Security. CIS 2006. Lecture Notes in Computer Science(), vol 4456. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74377-4_24
Download citation
DOI: https://doi.org/10.1007/978-3-540-74377-4_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74376-7
Online ISBN: 978-3-540-74377-4
eBook Packages: Computer ScienceComputer Science (R0)