Training Recurrent Networks Using the Extended Kalman Filter

Proceedings of the International Joint Conference on Neural Networks

Volumn 4, Issue , 1992, Pages 241-246

  Williams, Ronald J ^a  

^a NORTHEASTERN UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

RECURRENT NEURAL NETWORKS;

FINITE-STATE; FORCINGS; GENERALISATION; ON-LINE ALGORITHMS; REAL TIME RECURRENT LEARNING ALGORITHMS; RECURRENT NETWORKS; SIMPLE++; SPEED UP; TEACHERS'; TIME STEP;

EXTENDED KALMAN FILTERS;

EID: 85132302281     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/IJCNN.1992.227335     Document Type: Conference Paper

References (18)

1. Anderson, B. D. O. & Moore, J. B. (1979). Optimal Filtering. Englewood Cliffs, NJ: Prentice-Hall.
2. Bachrach, J. (1988). Learning to represent slate. Unpublished master's thesis. University of Massachusetts, Amherst, Department of Computer and Information Science.
3. Cleeremans, A., Servan-Schreiber, D., & McClelland, J. L. (1989). Finite-state automata and simple recurrent networks. Neural Computation, 1, 372-381.
4. Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14, 179-211.
5. Gelb, A., Ed. (1974). Applied Optimal Estimation. Cambridge, MA: MIT Press.
6. Matthews, M. B. (1990). Neural network nonlinear adaptive filtering using the extended Kalman filter algorithm. Proceedings of the International Neural Networks Conference, July, 1990, Paris, vol. I, pp. 115-119.
7. McBride, L. E., Jr. & Narendra, K. S. (1965). Optimization of time-varying systems. IEEE Transactions on Automatic Control, 10, 289-294.
8. Narendra, K. S., & Parthasarathy, K. (1990). Identification and control of dynamical systems using neural networks. IEEE Transactions on Neural Networks, 1, 4-27.
9. Puskorius, G. V. & Feldkamp, L. A. (1991). Decoupled extended Kalman filter training of feedforward layered networks. Proceedings of the International Joint Conference on Neural Networks, I, 771-777.
10. Robinson, A. J. & Fallside, F. (1987). The utility driven dynamic error propagation network (Technical Report CUED/F-1NFENG/TR.1). Cambridge, England: Cambridge University Engineering Department.
11. Rohwer, R. (1990). The "moving targets" training algorithm. Proceedings of the EURASIP Workshop on Neural Networks, Sesimbra, Portugal, 15-17 Feb. 1990, L. B. Almeida and C. J. Wellekens, Eds., Lecture Notes in Computer Science v. 412, p. 100, series Eds. G. Goos and J. Hartmanis, Springer-Verlag.
12. Singhal, S. & Wu, L. (1989). Training multilayer perceptrons with the extended Kalman filter algorithm. In D. S. Touretzky, Ed. Advances in Neural Information Processing Systems, 1, 133-140. San Mateo, CA: Morgan Kaufmann.
13. Widrow, B. & Stearns, S. D. (1985). Adaptive Signal Processing. Englewood Cliffs, NJ: Prentice-Hall.
14. Williams, R. J. (1992). Some observations on the use of the extended Kalman filter as a recurrent network learning algorithm (Technical Report NU-CCS-92-1). Boston: Northeastern University, College of Computer Science.
15. Williams, R. J. & Peng, J. (1990). An efficient gradient-based algorithm for on-line training of recurrent network trajectories. Neural Computation, 2, 490-501.
16. Williams, R. J., & Zipser, D. (1989). Experimental analysis of the real-time recurrent learning algorithm. Connection Science, 1, 87-111.
17. Williams, R. J. & Zipser, D. (1990). Gradientbased learning algorithms for recurrent connectionist networks, (Technical Report NU-CCS-90-9). Boston: Northeastern University, College of Computer Science.
18. Zipser, D. (1989). A subgrouping strategy that reduces complexity and speeds up learning in recurrent networks. Neural Computation, 1, 552-558.