An adaptive Bayesian pruning for neural networks in a non-stationary environment

Neural Computation

Volumn 11, Issue 4, 1999, Pages 965-976

  Sum, John ^a   Leung, Chi Sing ^d   Young, Gilbert H ^b   Chan, Lai Wan ^c   Kan, Wing Kay ^c  

^a HONG KONG BAPTIST UNIVERSITY   (Hong Kong)

^b HONG KONG POLYTECHNIC UNIVERSITY   (Hong Kong)

^c CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

^d NONE

Author keywords

[No Author keywords available]

Indexed keywords

ARTICLE; ARTIFICIAL NEURAL NETWORK; BAYES THEOREM; CHRONIC BRAIN DISEASE; FILTRATION; LEARNING; NORMAL DISTRIBUTION; TIME;

BAYES THEOREM; BRAIN DAMAGE, CHRONIC; FILTRATION; LEARNING; NEURAL NETWORKS (COMPUTER); NORMAL DISTRIBUTION; TIME FACTORS;

EID: 0033561887     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976699300016539     Document Type: Article

References (18)

1. Anderson, B. D. O., & Moore, J. (1979). Optimal filtering. Englewood Cliffs, NJ: Prentice Hall.
2. Finnoff, W., Hergert, F., & Zimmermann, H. G. (1993). Improving model selection by nonconvergent methods. Neural Networks, 6, 771-783.
3. Hassibi, B., & Stork, D. G. (1993). Second order derivatives for network pruning: Optimal brain surgeon. In J. D. Cowan, G. Tesauro, & J. Alspector (Eds.), Advances in neural information processing systems, 6 (pp. 164-171).
4. Iiguni, Y., Sakai, H., & Tokumaru, H. (1992). A real-time learning algorithm for a multilayered neural network based on the extended Kalman filter. IEEE Transactions on Signal Processing, 40(4), 959-966.
5. Kollias, S., & Anastassiou, D. (1989). An adaptive least squares algorithm for the efficient training of artificial neural networks. IEEE Transactions on Circuits and Systems, 36(8), 1092-1101.
6. Larsen J. (1996). Design of neural network filters. Unpublished doctoral disseration, Department of Mathematical Modeling, Technical University of Denmark.
7. LeCun, Y., Denker, J. S., & Solla, S. S. (1990). Optimal brain damage. In D. S. Touretzky (Ed.), Advances in neural information processing systems, 2 (pp. 396-404). San Mateo, CA: Morgan Kaufmann.
8. Leung, C. S., Wong, K. W., Sum, P. F., & Chan, L. W. (1996). On-line training and pruning for RLS algorithms. Electronics Letter, 32, 2152-2153.
9. MacKay, D. J. C. (1992). A practical Bayesian framework for backprop networks. Neural Computation, 4(3), 448-472.
10. MacKay, D. J. C. (1995). Bayesian methods for neural networks: Theory and applications. Course notes for Neural Networks Summer School. Available online at: http://wol.ra.phy.cam.ac.uk/mackay/cpi4.ps.gz.
11. Moody, J. (1994). Prediction risk and architecture selection for neural networks. In V. Cherkassky et al. (Eds.), From statistics to neural networks: Theory and pattern recognition application. Berlin: Springer-Verlag.
12. Prechelt, L. (1996). Comparing adaptive and non-adaptive connection pruning with pure early stopping. In Xu et al. (Eds.) Progress in neural information processing, 1 (pp. 46-52). Berlin: Springer-Verlag.
13. Prechelt, L. (1997). Connection pruning with static and adaptive pruning schedules, in press Neurocomputing.
14. Puskorius, G. V., & Feldkamp, L. A. (1994). Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks. IEEE Transactions on Neural Networks, 5(2), 279-297.
15. Reed, R. (1993), Pruning algorithms - A survey. IEEE Transactions on Neural Networks, 4(5), 740-747.
16. Shah, S., Palmeieri, F., & Datum, M. (1992). Optimal filtering algorithms for fast learning in feedforward neural networks. Neural Networks, 5, 779-787.
17. Singhal, S., & Wu, L. (1989). Training multilayer perceptrons with the extended Kalman algorithm. In D. S. Touretzky (Ed.), Advances in neural information processing systems, 1 (pp. 133-140). San Mateo, CA: Morgan Kaufmann.
18. Wan, E. A., & Nelson, A. T. (1996). Dual Kalman filtering methods for nonlinear prediction, smoothing, and estimation. In Advances in Neural Processing Systems 9, M. Mozer, M. Jordan, and T. Petsche (Eds.), 793-799, MIT Press, 1997.