Adaptive Behavior from Fixed Weight Networks

Information Sciences

Volumn 98, Issue 1-4, 1997, Pages 217-235

  Feldkamp, L A ^a   Puskorius, G V ^a   Moore, P C ^a  

^a FORD RESEARCH LABORATORY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE SYSTEMS; ARTIFICIAL INTELLIGENCE; COMPUTATION THEORY; COMPUTER ARCHITECTURE; LEARNING SYSTEMS;

ADAPTIVE BEHAVIOR; FIXED WEIGHT NETWORKS; NETWORK TRAINING PROCEDURES; SINGLE RECURRENT NETWORK;

NEURAL NETWORKS;

EID: 0031147647     PISSN: 00200255     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0020-0255(96)00216-2     Document Type: Article

References (14)

1. M. I. Jordan and R. A. Jacobs, Hierarchical mixtures of experts and the EM algorithm, Neural Computation 6:181-214 (1994).
2. M. Mangeas and A. Weigend, First experiments using a mixture of nonlinear experts for time series prediction, in: Proc. World Congress on Neural Networks, Vol. II, Washington, DC, 1995, pp. II-104-II-109.
3. N. E. Cotter and P. R. Conwell, Fixed-weight networks can learn, in: Proc. Int. Joint Conf. on Neural Networks, Vol. III, San Diego, CA, 1990, pp. 553-559.
4. N. E. Cotter and P. R. Conwell, Learning algorithms and fixed dynamics, in: Proc. Int. Joint Conf. on Neural Networks, Vol. I, Seattle, WA, 1991, pp. 799-804.
5. J. T. H. Lo and L. Yu, Adaptive neural filtering by using the innovations process, in: Proc. World Congress on Neural Networks, Vol. II, Washington, DC, 1995, pp. II-29-II-35.
6. G. V. Puskorius and L. A. Feldkamp, Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks, IEEE Trans. Neural Networks 5(2):279-297 (1994).
7. J. Hale and H. Koç, Dynamics and Bifurcations, Springer-Verlag, New York, 1991. (The form given here is somewhat different from the form frequently encountered.)
8. D. Kaplan and L. Glass, Understanding Nonlinear Dynamics, Springer-Verlag, New York, 1995.
9. R. J. Williams and D. Zipscr, A learning algorithm for continually running fully recurrent neural networks, Neural Computation 1:270-280 (1989).
10. G. V. Puskorius and L. A. Feldkamp, Decoupled extended Kalman filter training of feedforward layered networks, in: Proc. Int. Joint Conf. on Neural Networks, Vol. I, Seattle, WA, 1991, pp. 771-777.
11. G. V. Puskorius and L. A. Feldkamp, Avoiding matrix inversions for the decoupled extended Kalman filter training algorithm, in: Proc. World Congress on Neural Networks, Vol. I, Washington, DC, 1995, pp. I-704-I-709.
12. E. S. Plumer, Training neural networks using sequential extended Kalman filtering, in: Proc. World Congress on Neural Networks, Vol. I, Washington, DC, 1995, pp. I-764-I-769.
13. L. A. Feldkamp and G. V. Puskorius, Training controllers for robustness: Multistream DEKF, in: Proc. IEEE Int. Conf. on Neural Networks, Vol. IV, Orlando, FL, 1994, pp. 2377-2382.
14. L. A. Feldkamp and G. V. Puskorius, Training of robust neural controllers, in: Proc. 33rd IEEE Int. Conf. on Decision and Control, Vol. III, Orlando, FL, 1994, pp. 2754-2760.