Recurrent neural networks training with stable risk-sensitive Kalman filter algorithm

Proceedings of the International Joint Conference on Neural Networks

Volumn 2, Issue , 2005, Pages 700-705

  Yu, Wen ^a   De Jesús Rubio, José ^a   Li, Xiaoou ^a  

^a DEPARTAMENTO DE FÍSICA   (Mexico)

Author keywords

[No Author keywords available]

Indexed keywords

CONVERGENCE OF NUMERICAL METHODS; KALMAN FILTERING; LEARNING ALGORITHMS; NONLINEAR CONTROL SYSTEMS; STABILITY; STATE SPACE METHODS;

COST CRITERION; INPUT-TO-STATE STABILITY; KALMAN FILTER-BASED ALGORITHM; RISK-SENSITIVE;

RECURRENT NEURAL NETWORKS;

EID: 33745965821     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/IJCNN.2005.1555937     Document Type: Conference Paper

References (17)

1. R. K. Boel, M.R. James and I.R.Petersen, Robustness and Risk-Sensitive Filtering, IEEE Trans. Automatic Control, Vol.47, No.3, 451-462, 2002.
2. F. N. Chowdhury, A new approach to real-time training of dynamic neural networks, International Journal of Adaptive Control and Signal Processing, 509-521, 2003. 984.
3. S.Dey and J.B. Moore, Finite-Dimensional Risk-Sensitive Filters and Smooters for Discrete-Time Nonlinear Systems, IEEE Trans. Automatic Control, Vol.44, No.6, 1234-1239, 1999.
4. S. Haykin, Neuronal Networks, Macmillan Pub.Co., Second edition, Englewood cliffs, NJ 17458, 1999.
5. Y. Iiguni, H. sakai, Member, IEEE and Higekatsu Tokumaru, A Real-Time Learning Algorithm for a Multilayered Neural Network Based on the Extended Kalman Filter, IEEE Transactions on Signal Processing, Vol.40, No.4, 959-966, April 1992.
6. M. Jayakumar and R.N. Banavar, Risk-Sensitive Filters for Recursive Estimation of Motion From Images, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.20, No.6, 659-667, 1998
7. J.T.Lo and T.Wanner, Existence and Uniqueness of Risk-Sensitive Estimates, IEEE Trans. Automatic control, vol.47, No.11, 1945-1
8. K.S.Narendra and K.Parthasarathy, Identification and control of Dynamical Systems using Neural Netwoks, IEEE Trans. Neural Networks, Vol.1, No.1, 4-27, 1990.
9. A. G. Parlos, S. K. Menon and A. F. Atiya, An Algorithm Approach to Adaptive State Filtering Using Recurrent Neural Network, IEEE Transactions on Neural Networks, vol.12, No.6, 1411-1432, 2001.
10. K. Reif and R. Unbehauen, The Extended Kalman Filter as an Exponential Observer for Nonlinear Systems, IEEE Transactions on Signal Processing, vol.47, No.8, 2324-2328, August 1999.
11. D. W. Ruck, S. K. Rogers, M. Kabrisky, P. S. Maybeck and M. E. Oxley, Comparative Analysis of Backpropagation and the Extended Kalman Filter for Training Multilayer Perceptrons. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 14, No.6, 686-691, June 1992.
12. G. V. Puskorius and L. A. Feldkamp, Neurocontrol of Nonlinear Dynamical Systems with Kalman Filter Trained Recurrent Networks, IEEE Transactions on Neural Networks, Vol.5, No.2, 279-297, March 1994.
13. S. Shah F. Palmeieri and M. Datum, Optimal filtering algorithms for fast learning in feed forward neural networks, Neural Networks, Vol.5, 779-787, 1992.
14. S. Singhal and L. Wu, Training multilayer perceptrons with the extended Kalman algorithm, Advances in Neural inform. Processing Syst. 1, 133-140, 1989.
15. P. Whitle, Risk-sensitive Optimal Control, John Wiley & sons, NY 10158-0012, USA, 1990.
16. K. W. Wong, C. S. Leung and S. J. Chang., Use of periodic and monotonic activation functions in multilayer feedforward neural networks trained by extended Kalman filter algorithm, IEE Image Signal Process, Vol.149, 217-224, August 2002.
17. W.Yu, Nonlinear system identification using descrete-time recurrent neural networks with stable learning algorithms, Information Sciences, Vol.158, No.1, 131-147, 2004.949, 2002.