Query-based learning for aerospace applications

IEEE Transactions on Neural Networks

Volumn 14, Issue 6, 2003, Pages 1437-1448

  Saad, Emad W ^a   Choi, Jai J ^b,c   Vian, John L ^a   Wunsch, Donald C ^d  

^a SOUTHERN METHODIST UNIVERSITY   (United States)

^b BOEING COMPANY   (United States)

^c UNIVERSITY OF WASHINGTON   (United States)

^d MISSOURI UNIVERSITY OF SCIENCE AND TECHNOLOGY   (United States)

Author keywords

Active learning; Aerospace application; Causality index (CI); Control distribution; Crew escape system; Efficient training; Emergency egress safety; Mapping; Network inversion; Node decoupled extended Kalman filter (NDEKF); Pattern recognition; Query based learning (QBL)

Indexed keywords

AEROSPACE APPLICATIONS; COMPUTER SIMULATION; CONFORMAL MAPPING; FIGHTER AIRCRAFT; HEURISTIC METHODS; JET AIRCRAFT; KALMAN FILTERING; NEURAL NETWORKS; PATTERN RECOGNITION; QUERY LANGUAGES; SPACECRAFT ESCAPE SYSTEMS; VECTORS;

ACTIVE LEARNING; CASUALITY INDEX; CREW ESCAPE SYSTEM; EMERGENCY EGRESS SAFETY; INVERSE MAPPING; NETWORK INVERSION; NODE DECOUPLED EXTENDED KALMAN FILTER; QUERY BASED LEARNING;

LEARNING SYSTEMS;

EID: 0742303650     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2003.820826     Document Type: Article

References (38)

1. J. Hwang, J. Choi, S. Oh, and R. Marks, II, "Query-based learning applied to partially trained multilayer perceptrons," IEEE Trans. Neural Networks, vol. 2, pp. 131-136, Jan. 1991.
2. ____, "Query learning based on boundary search and gradient computation of trained multilayer perceptrons," in Proc. Int. Joint Conf. Neural Networks, San Diego, 1990, pp. 57-62.
3. S. Oh, R. Marks II, and M. El-Sharkawi, "Query based learning in a multilayered perception in the presence of data jitter," in Proc. First Int. Forum on Applications of Neural Networks for Power Systems, pp. 567-62.
4. J. Hwang and H. Li, "Interactive query learning for isolated speech recognition," in Proc. IEEE-SP Workshop on Neural Networks for Signal Processing II, pp. 93-102.
5. D. Cohn, "Neural network exploration using optimal experiment design," Neural Networks, 9, no. 6, pp. 1071-1083, 1996.
6. K. Fukumizu, "Statistical active learning in multilayer perceptrons," IEEE Trans. Neural Networks, vol. 11, 2000.
7. V. Fedorov, Theory of Optimal Experiments. New York: Academic, 1972.
8. D. MacKay, "Information-based objective functions for active data selection," Neural Computation, vol. 4, no. 4, pp. 589-603.
9. J. Ratsaby, "Incremental learning with sample queries," IEEE Trans. Pattern Anal. Machine Intell., vol. 20, pp. 883-888, 1998.
10. C. Christian, "Pedagogical pattern selection strategies," Neural Networks, vol. 7, no. 1, pp. 175-181, 1994.
11. D. Angluin, "A note on the number of queries needed to identify regular languages," Inform. Contr., vol. 51, pp. 76-87, 1982.
12. D. Cohn, L. Atlas and R. Ladner, "Training connectionist networks with queries and selective sampling," in Advances in Neural Information Processing Systems 2, D. Touretzky, Ed. Cambridge, MA: MIT Press, 1990.
13. E. Baum, and K. Lang, "Neural network algorithms that learnn in polynomial time from examples and queries," IEEE Trans. Neural Networks, vol. 2.
14. A. Linden and J. Kindermann, "Inversion of multilayer nets," in Proc. Int. Joint Conf. Neural Networks, vol. II, Wash., DC, 1989, pp. 425-430.
15. S. Haykin, Neural Networks: A Comprehensive Foundation. Englewood Cliffs, NJ: Prentice-Hall, 1998.
16. P. Werbos, "Backpropagation through time: What it does and how to do it," Proc. IEEE. vol. 7, pp. 1550-1560, 1990.
17. R. Reed, R. J. Marks II, and S. Oh, "Similarities of error regularization, sigmoid gain scaling, target smoothing, and training with jitter," IEEE Trans. Neural Networks, vol. 6, pp. 529-538, 1995.
18. R. Reed, S. Oh, and R. J. Marks, II, "An equivalence between sigmoidal gain scaling and training with noisy (jittered) input data," in Proc. RNNS/IEEE Symp. Neuroinformatics Neurocomputing, Rostov-on-Don, Russia, 1992.
19. D. C. Plaut, S. J. Nowlan, and G. E. Hinton, "Experiments on learning in a multilayered perception in the presence of data jitter," Carnegie-Mellon Univ., Tech. Rep. CMU-CS-86-126, 1986.
20. J. L. Elman and D. Zipser, "Learning the hidden structure of speech," J. Accoust. Soc. Amer., vol. 83, no. 4, pp. 1615-1626, 1988.
21. P. Refregier and J. M. Vignolle, "An improved version of the pseudo-inverse solution for classification and neural networks," Europhys. Lett., vol. 10, no. 4 pp. 387-392, 1989.
22. A. S. Weigend, D. E. Rumelhart, and B. A. Huberman, "Generalization by weight-elimination applied to currency exchange rate prediction," in Proc. Int. Joint Conf. Neural Networks, vol. I, Seattle, WA, 1991, pp. 837-841.
23. J. Sietsma and R. J. F. Dow, "Creating artificial neural networks that generalized," Neural Networks, vol. 4, no. 1, pp. 67-79, 1991.
24. S. Oh, R. J. Marks, II, and M. A. El-Sharkawi, "Query based learning in a multilayered perceptron in the presence of data jitter," in Applications of Neural Networks to Power Systems, M. S. El-Sharkawi and R. J. Marks, II, Eds. New York: IEEE, 1991, pp. 72-75.
25. C. H. Séquin and R. D. Clay, "Fault tolerance in feed-forward articial neural networks," in Neural Networks: Concepts, Applications, and Implementations, P. Antognetti and V. Milutinovié, Eds. Englewood Cliffs, NJ: Prentice-Hall, 1991, vol. IV, pp. 111-141.
26. J. I. Minnix, "Fault tolerance of the backpropagation neural network trained on noisy inputs," in Proc. Int. Joint Conf. Neural Networks, vol. I, Baltimore, MD, 1992, pp. 847-852.
27. D. A. Cohn, Z. Ghahramani, and M. I. Jordan, "Active learning with statistical models", J. Artific. Intell. Res., vol. 4, pp. 129-145, 1996.
28. K. Baba, I. Enbutu, and M. Yoda, "Explicit representation of knowledge acquired from plant historical data using neural network," in Proc. Int. Joint Conf. on Neural Networks, vol. II. Washington, 1992, pp. 579-583.
29. Z. Boger, "Knowledge extraction from artificial neural networks models," in Proc. IEEE Int. Conf. on Syst., Man and Cybern., vol. 4, Orlando, FL, 1997, pp. 3030-3035.
30. B. Mak and R. Blanning, "An empirical measure of element contribution in neural networks," IEEE Trans. Syst., Man and Cybern., vol. 28, pp. 561-564, 1998.
31. E. W. Saad, D. V. Prokhorov, and D. C. Wunsch, II, "Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks," IEEE Trans. Neural Networks, vol. 9, no. 6, 1998.
32. E. W. Saad, J. J. Choi, J. L. Vian, and D. C. Wunsch, II, "Efficient training techniques for classification with vast input space," in Proc. Int. Joint Conf. Neural Networks, Wash., DC, 1999.
33. EASY5 User's Guide, The Boeing Company, Seattle, WA, 1997.
34. S. Singhal and L. Wu, "Training multilayer perceptions with the extended Kalman algorithm," in Advances in Neural Information Processing Systems 1, D. S. Touretsky, Ed. San Mateo, CA: Morgan Kaufmann, 1989, pp. 133-140.
35. G. V. Puskorius and L. A. Feldkamp, "Role of learning rates, artificial process noise and square root filtering for extended Kalman filter training," in Proc. Int. Joint Conf. Neural Networks, Wash., DC, July 1999.
36. ____, "Decoupled extended Kalman filter training of feedforward layered networks," in Proc. Int. Joint Conf. Neural Networks, vol. I, Seattle, WA, 1991, pp. 771-777.
37. L. Prechelt, "Automatic early stopping using cross validation: Quantifying the criteria," Neural Networks, vol. 11, no. 4, pp. 761-767, 1998.
38. J. L. Vian and N. A. Visnevski, "Neural Networks for Nonlinear Control Distribution," in Proc. Int. Federation of Automatic Control: 3rd Symp. Intelligent Components and Instruments for Control Applications, Annecy, France, 1997, pp. 229-234.