Adaptive training and pruning in feedforward networks

Electronics Letters

Volumn 37, Issue 2, 2001, Pages 106-107

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

^a NANKAI UNIVERSITY   (China)

^b CITY UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; CHARACTER RECOGNITION; COMPUTATIONAL COMPLEXITY; ITERATIVE METHODS; KALMAN FILTERING;

HANDWRITTEN DIGIT RECOGNITION;

FEEDFORWARD NEURAL NETWORKS;

EID: 0035136577     PISSN: 00135194     EISSN: None     Source Type: Journal    
DOI: 10.1049/el:20010074     Document Type: Article

References (4)

1. IIGUNL, Y., SAKAI, H., and TOKUMARU, H.: 'Real-time learning algorithm for a multilayered neural network based on the extended Kalman filter', IEEE Trans. Signal Process., 1992, 40, pp. 959-967
2. SUM, J., LEUNG, C.S., YOUNG, G.H., and KAN, W.K.: 'On the Kalman filtering method in neural-network training and pruning', IEEE Trans. Neural Netw., 1999, 10, pp. 161-166
3. PENG, H., SHA, L., GAN, Q., and WEI, Y.: 'Energy function for learning invariant in multilayer perceptron', Electron. Lett., 1998, 34, pp. 292-294
4. WALLIS, G.: 'Using spatio-temporal correlations to learn invariant object recognition', Neural Netw., 1996, 9, pp. 1513-1519