A new approach to real-time training of dynamic neural networks

International Journal of Adaptive Control and Signal Processing

Volumn 17, Issue 6, 2003, Pages 509-521

  Chowdhury, Fahmida N ^a  

^a UNIVERSITY OF LOUISIANA AT LAFAYETTE   (United States)

Author keywords

Dynamic systems; Input output modelling; Kalman filter; Real time training

Indexed keywords

KALMAN FILTERING; NEURAL NETWORKS; RANDOM PROCESSES; TIME VARYING SYSTEMS; VECTORS;

DYNAMIC SYSTEMS;

REAL TIME SYSTEMS;

EID: 0042364961     PISSN: 08906327     EISSN: None     Source Type: Journal    
DOI: 10.1002/acs.756     Document Type: Article

References (9)

1. Narendra KS, Parthasarathy K. Identification and control of dynamic systems using neural networks. IEEE Transactions on Neural Networks 1990; 1(1):4-27.
2. Werbos PJ, McAvoy T, Su T. Neural networks, system identification, and control in the chemical process industries. In Handbook of Intelligent Control, White, Sofge (eds). Van Nostrand Reinhold: New York, 1992; 283-356.
3. Hassoun MH. Fundamentals of Articial Neural Networks. MIT Press: Cambridge, MA, 1995; 259-261.
4. Hovakimyan N, Lee H, Calise AJ. On approximate NN realization of an unknown dynamic system from its input-output history. Proceedings of the American Control Conference, Chicago, US, 2000; Paper N WM17-1.
5. Iiguni Y, Sakai H, Tokumaru H. A real-time learning algorithm for a multilayered neural network based on the extended Kalman filter. IEEE Transactions on Signal Processing 1992; 40(4):959-966.
6. Nicolao GD, Ferrari-Trecate G. Regularization networks: fast weight calculation via Kalman filtering. IEEE Transactions on Neural Networks 2001; 12(2):228-235.
7. Sum J, Leung C, Young GH, Kan W. On the Kalman filtering method in neural network training and pruning. IEEE Transactions on Neural Networks 1999; 10(1):161-166.
8. Zhang Y, Li XR, A fast U-D factorization-based learning method with applications to nonlinear system modeling and identification. IEEE Transactions on Neural Networks 1999; 10(4):930-938.
9. Chowdhury FN, Kotta Ü, Nõmm S. On realizability of neural networks based input-output models. Proceedings of the Differential Equations and Applications 2000. St Petersburg, Russia.