The Adaptive Learning Rates of Extended Kalman Filter Based Training Algorithm for Wavelet Neural Networks
Since the convergence of neural networks depends on learning rates, the learning rates of training algorithm for neural networks are very important factors. Therefore, we propose the Adaptive Learning Rates(ALRs) of Extended Kalman Filter(EKF) based training algorithm for wavelet neural networks(WNNs). The ALRs of the EFK based training algorithm produce the convergence of the WNN. Also we derive the convergence analysis of the learning process from the discrete Lyapunov stability theorem. Several simulation results show that the EKF based WNN with ALRs adapt to abrupt change and high nonlinearity with satisfactory performance.
KeywordsExtend Kalman Filter Asymptotic Convergence Wavelet Neural Network Past Output Adaptive Learn Rate
Unable to display preview. Download preview PDF.
- 1.Slotin, J.E., Li, W.: Applied Nonlinear Control. Prentice-Hall, Englewood Cliffs (1991)Google Scholar
- 3.Yoo, S.J., Park, J.B., Choi, Y.H.: Stable Predictive Control of Chaotic Systems Using Self-Recurrent Wavelet Neural Network. Int. Journal of Control, Automation, and Systems 3, 43–55 (2005)Google Scholar
- 5.Oh, J.S., Park, J.B., Choi, Y.H.: Path Tracking Control using a Wavelet Neural Network for Mobile Robot with Extended Kalman Filter. In: Proc. of the Int. Conf. Control, Automation and Systems, pp. 1283–1288 (2003)Google Scholar
- 7.Yoo, S.J., Park, J.B., Choi, Y.H.: Direct Adaptive Control Using Self Recurrent Wavelet Neural Network Via Adaptive Learning Rates for Stable Path Tracking of Mobile Robots. In: Proc. of American Control Conference, vol. 1, pp. 288–293 (2005)Google Scholar
- 8.Singhal, S., Wu, L.: Training Feed-forward Networks with the Extended Kalman Algorithm. In: Proc. of Int. Conf. on Acoustics, Speech, and Signal Processing, vol. 2, pp. 1187–1190 (1989)Google Scholar
- 9.Wu, Q., Saif, M.: Neural Adaptive Observer Based Fault Detection and Identification for Satellite Attitude Control Systems. In: Proc. of American Control Conference, vol. 2, pp. 1054–1059 (2005)Google Scholar
- 12.Alessandri, A., Cuneo, M., Pagnan, S., Sanguineti, M.: On the Convergence of EKF-Based Parameters Optimization for Neural Networks. In: Proc. of 42nd IEEE Conference on Decision and Control, vol. 6, pp. 6181–6186 (2003)Google Scholar