Training feedforward neural networks: an algorithm giving improved generalization
作者： Charles W. Lee
DOI: 10.1016/S0893-6080(96)00071-8
关键词:
摘要: Abstract An algorithm is derived for supervised training in multilayer feedforward neural networks. Relative to the gradient descent backpropagation it appears give both faster convergence and improved generalization, whilst preserving system of backpropagating errors through network. Copyright © 1996 Elsevier Science Ltd.
elsevier.com
sci-hub.se 参考文章(16)
Anthony N. Burkitt, Optimization of the Architecture of Feed-forward Neural Networks with Hidden Layers by Unit Elimination Complex Systems. ,vol. 5, ,(1991)
Merten Joost, Wolfram Schiffmann, Randolf Werner, Comparison of optimized backpropagation algorithms. the european symposium on artificial neural networks. ,(1993)
T. J. Sejnowski, Parallel networks that learn to pronounce English text Complex Systems. ,vol. 1, pp. 145- 168 ,(1987)
David E. Rumelhart, James L. McClelland, , Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations Computational Models of Cognition and Perception. ,(1986) , 10.7551/MITPRESS/5236.001.0001
W. H. Wolberg, O. L. Mangasarian, Multisurface Method of Pattern Separation for Medical Diagnosis Applied to Breast Cytology Proceedings of the National Academy of Sciences of the United States of America. ,vol. 87, pp. 9193- 9196 ,(1990) , 10.1073/PNAS.87.23.9193
Charles W. Lee, Learning in neural networks by using tangent planes to constraint surfaces Neural Networks. ,vol. 6, pp. 385- 392 ,(1993) , 10.1016/0893-6080(93)90005-H
G.C. Lendaris, I.A. Harb, Improved generalization in ANNs via use of conceptual graphs: a character recognition task as an example case international joint conference on neural network. pp. 551- 556 ,(1990) , 10.1109/IJCNN.1990.137624
Ryotaro Kamimura, Internal representation with minimum entropy in recurrent neural networks: minimizing entropy through inhibitory connections Network: Computation In Neural Systems. ,vol. 4, pp. 423- 440 ,(1993) , 10.1088/0954-898X_4_4_002
Jun Wang, B. Malakooti, Characterization of training errors in supervised learning using gradient-based rules Neural Networks. ,vol. 6, pp. 1073- 1087 ,(1993) , 10.1016/S0893-6080(09)80019-1
E.D. Karnin, A simple procedure for pruning back-propagation trained neural networks IEEE Transactions on Neural Networks. ,vol. 1, pp. 239- 242 ,(1990) , 10.1109/72.80236