Combining DEKF algorithm and trace rule for fast on-line invariance extraction and recognition

Pattern Recognition Letters

Volumn 21, Issue 6-7, 2000, Pages 493-501

  Chang, Sheng Jiang ^a   Wong, Kwok Wo ^a   Leung, Chi Sing ^a  

^a CITY UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

EKF Algorithm; Neural networks; Pattern recognition; Pruning; Trace Rule

Indexed keywords

ALGORITHMS; COMPUTER SIMULATION; FEATURE EXTRACTION; KALMAN FILTERING; NEURAL NETWORKS;

DUAL EXTENDED KALMAN FILTER (DEKF) ALGORITHM; TRACE RULE;

OPTICAL CHARACTER RECOGNITION;

EID: 0033729381     PISSN: 01678655     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-8655(00)00013-1     Document Type: Article

References (17)

1. Chang S.J., Wong K.W, Leung C.S. Periodic activation function for fast on-line EKF training and pruning. Electronics Letters. 34:1998;2255-2256.
2. Foldiak P. Learning invariance from transformation sequence. Neural Computation. 3:1991;194-200.
3. Iiguni Y., Sakai H., Tokumaru H. Real-time learning algorithm for a multilayered neural network based on the extended Kalman filter. IEEE Transactions on Signal Processing. 40:1992;959-967.
4. LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D. Backpropagation applied to handwritten zip code recognition. Neural Computation. 1:1989;541-551.
5. Leung C.S., Wong K.W., Sum P.F., Chan L.W. On-line training and pruning for recursive least square algorithms. Electronics Letters. 32:1996;2152-2153.
6. Lovell, D.R., Tsoi, A.C., 1992. The performance of the neocognitron with various S-cell and C-cell transfer functions. Paper posted to the Connectionists internet mail group. Produced in the Department of Electrical Engineering, University of Queesland, Queesland 4072, Australia.
7. Peng H., Sha L., Gan Q., Wei Y. Energy function for learning invariant in multilayer perceptron. Electronics Letters. 34:1998a;292-294.
8. Peng H., Sha L., Gan Q., Wei Y. Combining adaptive sigmoid packet and trace neural network for fast invariance-learning. Electronics Letters. 34:1998b;898-899.
9. Prechelt L. Connection pruning with static and adaptive pruning schedules. Neurocomputing. 16:1997;49-61.
10. Prechelt L. Automatic early stopping using cross validation: quantifying the criteria. Neural Networks. 11:1998;761-767.
11. Reed R. Pruning algorithm - a survey. IEEE Transactions on Neural Networks. 11:1993;740-747.
12. Robbins H., Monro S. A stochastic approximation method. Ann. Math. Stat. 22:1951;400-407.
13. Shah S., Palmieri F. Optimal filtering algorithm for fast learning in feedforward neural networks. Neural Networks. 5:1992;779-787.
14. Singhal S., Wu L. Training feed-forward network with the extended Kalman filter. Proceedings of IEEE International Conference on Acoustics Speech and Signal Processing. 1989;1187-1190.
15. Tesauro G., He Y., Ahmad S. Asymptotic convergence of backpropagation. Neural Computation. 1:1989;382-391.
16. Wallis G. Using spatio-temporal correlations to learn invariant object recognition. Neural Networks. 9(9):1996;1513-1519.
17. Wallis G., Baddeley R. Optimal, unsupervised learning in invariant object recognition. Neural Computation. 9(4):1997;883-894.