A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering, and classification

Proceedings of the IEEE

Volumn 86, Issue 11, 1998, Pages 2259-2277

  Feldkamp, Lee A ^a,b,c,d   Puskorius, Gintaras V ^a,d  

^a FORD RESEARCH LABORATORY   (United States)

^b Board of Governors of the International Neural Network Society   (United States)

^c AMERICAN PHYSICAL SOCIETY   (United States)

^d IEEE   (United States)

Author keywords

Automotive diagnostics; Backpropagation through time; Kalman filtering; Lime series prediction; Multistream training; Recurrent multilayer perceptrons; Recurrent networks; Stability; System identification

Indexed keywords

ADAPTIVE FILTERING; BACKPROPAGATION; ERROR ANALYSIS; KALMAN FILTERING; LEARNING SYSTEMS; MULTILAYER NEURAL NETWORKS; NONLINEAR FILTERING; RECURRENT NEURAL NETWORKS; SYSTEM STABILITY; TIME SERIES ANALYSIS;

AUTOMOTIVE DIAGNOSTICS; MULTISTREAM TRAINING; TIME SERIES PREDICTIONS;

DIGITAL SIGNAL PROCESSING;

EID: 0032203999     PISSN: 00189219     EISSN: None     Source Type: Journal    
DOI: 10.1109/5.726790     Document Type: Article

References (28)

1. q theory: Checking and imposing stability of recurrent neural networks for nonlinear modeling," IEEE Trans. Signal Processing, vol. 45, pp. 2682-2691, Nov. 1997.
2. S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed. Upper Saddle River, NJ: Prentice-Hall, 1994.
3. C. M. Bishop, Neural Networks for Pattern Recognition. Oxford, UK: Oxford, 1995.
4. R. J. Williams, "Adaptive state representation and estimation using recurrent connectionist networks," in Neural Networks for Control, W. T. Miller III, R. S. Sutton, and P. J. Werbos, Eds. Cambridge, MA: MIT, 1990, pp. 97-114.
5. J. T.-H. Lo, "System identification by recurrent multilayer perceptrons," in Proc. World Congr. Neural Networks, Portland, OR, 1993, pp. IV-589-IV-600.
6. K. Hornik, M. Stinchcombe, and H. White, "Multilayer feedforward networks are universal approximators," Neural Networks, vol. 2, pp. 359-366, 1989.
7. N. E. Cotter and P. R. Conwell, "Fixed-weight networks can learn," in Proc. Int. Joint Conf. Neural Networks, San Diego, CA, 1990, vol. III, pp. 553-559.
8. _, "Learning algorithms and fixed dynamics," in Proc. Int. Joint Conf. Neural Networks, Seattle, WA, vol. I, 1991, pp. 799-804.
9. L. A. Feldkamp, G. V. Puskorius, and P. C. Moore, "Adaptive behavior from fixed weight networks," Information Sciences, vol. 98, pp. 217-235, 1997.
10. _, "Adaptation from fixed weight dynamic networks," in Proc. IEEE Int. Conf. Neural Networks, Washington DC, 1996, pp. 155-160.
11. P. J. Werbos, "Backpropagation through time: What it does and how to do it," Proc. IEEE, vol. 78, pp. 1550-1560, Oct. 1990.
12. G. V. Puskorius, L. A. Feldkamp, and L. I. Davis, Jr., "Dynamic neural network methods applied to on-vehicle idle speed control," Proc. IEEE, vol. 84, pp. 1407-1420, Oct. 1996.
13. K. S. Narendra and K. Parthasarathy, "Identification and control of dynamical systems containing neural networks," IEEE Trans. Neural Networks, vol. 1, pp. 4-27, Jan. 1990.
14. G. V. Puskorius and L. A. Feldkamp, "Neurocontrol of non-linear dynamical systems with Kalman filter trained recurrent networks," IEEE Trans. Neural Networks, vol. 5, pp. 279-297, Mar. 1994.
15. R. J. Williams and J. Peng, "An efficient gradient-based algorithm for on-line training of recurrent network trajectories," Neural Computation, vol. 2, pp. 490-501, 1990.
16. S. Singhal and L. Wu, "Training multilayer perceptrons with the extended Kalman algorithm," in Advances in Neural Information Processing Systems 1, D. S. Touretzky, Ed. San Mateo, CA: Morgan Kaufmann, 1989, pp. 133-140.
17. B. D. O. Anderson and J. B. Moore, Optimal Filtering. Englewood Cliffs, NJ: Prentice-Hall, 1979.
18. S. Haykin, Adaptive Filter Theory. Englewood Cliffs, NJ: Prentice-Hall, 1996.
19. G. V. Puskorius and L. A. Feldkamp, "Decoupled extended Kalman filter training of feedforward layered networks," in Proc. Int. Joint Conf. Neural Networks, Seattle, WA, 1991, vol. I, pp. 771-777.
20. M. B. Matthews, "Neural network nonlinear adaptive filtering using the extended Kalman filter algorithm," in Proc. Int. Neural Networks Conf., Paris, 1990, vol. I, pp. 115-119.
21. R. J. Williams, "Training recurrent networks using the extended Kalman filter," in Proc. Int. Joint Conf. Neural Networks, Baltimore, 1992, vol. IV, pp. 241-246.
22. L. A. Feldkamp and G. V. Puskorius, "Training of robust neural controllers," in Proc. 33rd IEEE Int. Conf. Decision and Control, Orlando, FL, 1994, vol. III, pp. 2754-2760.
23. G. V. Puskorius and L. A. Feldkamp, "Extensions and enhancements of decoupled extended Kalman filter training," in Proc. 1997 Int. Conf. Neural Networks, Houston TX, vol. 3, pp. 1879-1883.
24. A. H. Sayed and T. Kailath, "A state-space approach to adaptive RLS filtering," IEEE Signal Processing Mag., vol. 11, pp. 18-60, Mar. 1994.
25. Y. Bengio, P. Simard, and P. Frasconi, "Learning long-term dependencies with gradient descent is difficult," IEEE Trans. Neural Networks, vol. 5, pp. 157-166, Mar. 1994.
26. G. V. Puskorius and L. A. Feldkamp, "Signal processing by dynamic neural networks with application to automotive misfire detection," in Proc. World Cong. Neural Networks, San Diego, 1996, pp. 585-590.
27. K. A. Marko, J. V. James, T. M. Feldkamp, G. V. Puskorius, L. A. Feldkamp, and D. Prokhorov, "Training recurrent networks for classification: Realization of automotive engine diagnostics," in Proc. World Congr. Neural Networks, San Diego, CA, 1996, pp. 845-850.
28. R. Tawel, N. Aranki, G. V. Puskorius, K. A. Marko, L. A. Feldkamp, J. V. James, G. Jesion, and T. M. Feldkamp, "Custom VLSI ASIC for automotive applications with recurrent networks," Proc. 1998 Int. Joint Conf. Neural Networks, Anchorage AK, vol. 3, pp. 598-602.