Extensions and enhancements of decoupled extended Kalman filter training

IEEE International Conference on Neural Networks - Conference Proceedings

Volumn 3, Issue , 1997, Pages 1879-1883

  Puskorius, G V ^a   Feldkamp, L A ^a  

^a FORD RESEARCH LABORATORY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DECOUPLED EXTENDED KALMAN FILTERS; MEAN SQUARED ERROR; NETWORK WEIGHTS; PATTERN CLASSIFICATION PROBLEMS; RELATIVE ENTROPY; TRAINING COMPLEXITY; WEIGHT VALUES;

COMPLEX NETWORKS; EXTENDED KALMAN FILTERS; APPROXIMATION THEORY; COMPUTATIONAL COMPLEXITY; ERROR ANALYSIS; KALMAN FILTERING; OPTIMIZATION; PATTERN RECOGNITION;

NEURAL NETWORKS;

DECOUPLED EXTENDED KALMAN FILTER (DEKF);

EID: 0030682701     PISSN: 10987576     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICNN.1997.614185     Document Type: Conference Paper

References (9)

1. G. V. Puskorius and L. A. Feldkamp, "Decoupled extended Kalman filter training of feedforward layered networks," in International Joint Conference on Neural Networks, Seattle, 1991, vol. I, pp. 771-777.
2. G. V. Puskorius and L. A. Feldkamp, "Recurrent network training with the decoupled extended Kalman filter algorithm," in Proceedings of the 1992 SPIE Conference on the Science of Artificial Neural Networks, Orlando, 1992, vol. 1710, pp. 461-473.
3. L. A. Feldkamp, G. V. Puskorius, and P. C. Moore, "Adaptation from fixed weight dynamic networks," in Proceedings of the IEEE International Conference on Neural Networks, Washington, D.C., 1996, pp. 155-160.
4. G. V. Puskorius and L. A. Feldkamp, "Neurocon-trol of Nonlinear Dynamical Systems with Kalman Filter Trained Recurrent Networks," IEEE Transactions on Neural Networks, vol. 5, no. 2, pp. 279-297, 1994.
5. G. V. Puskorius, L. A. Feldkamp, and L. I. Davis, Jr., "Dynamic neural network methods applied to on-vehicle idle speed control," Proceedings of the IEEE, vol. 84, no. 10, pp. 1407-1420, 1996.
6. D. L. Elliott, "A better activation function for artificial neural networks," Institute for Systems Research, Univ. of Maryland, Technical Report TR93-8 (1993).
7. J. Hertz, A. Krogh, and R. G. Palmer, Introduction to the Theory of Neural Computation. Redwood City, CA: Addison Wesley, 1991.
8. G. V. Puskorius and L. A. Feldkamp, "Avoiding matrix inversions for the decoupled extended Kalman filter training algorithm," in Proceedings of the World Congress on Neural Networks, Washington, D.C., 1995, pp. I-704-I-709.
9. E. S. Plumer, "Training neural networks usings sequential extended Kalman filtering," in Proceedings of the World Congress on Neural Networks, Washington, D.C., 1995, pp. I-764-I-769.