Theory of the backpropagation neural network

作者: Hecht-Nielsen

DOI: 10.1109/IJCNN.1989.118638

关键词:

摘要: The author presents a survey of the basic theory backpropagation neural network architecture covering architectural design, performance measurement, function approximation capability, and learning. includes previously known material, as well some new results, namely, formulation to make it valid (past formulations violated locality processing restriction) proof that mean-squared-error exists is differentiable. Also included theorem showing any L/sub 2/ from (0, 1)/sup n/ R/sup m/ can be implemented desired degree accuracy with three-layer network. speculative neurophysiological model illustrating how might plausibly in mammalian brain for corticocortical learning between nearby regions cerebral cortex. >

参考文章(31)
Yann Le Cun, Modèles connexionnistes de l'apprentissage Intellectica. ,vol. 2, pp. 114- 143 ,(1987) , 10.3406/INTEL.1987.1804
Yann Lecun, S. Becker, Improving the convergence of back-propagation learning with second-order methods Morgan Kaufmann. pp. 29- 37 ,(1989)
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams, Learning representations by back-propagating errors Nature. ,vol. 323, pp. 696- 699 ,(1988) , 10.1038/323533A0
B. WIDROW, M. E. HOFF, Adaptive switching circuits Neurocomputing: foundations of research. pp. 123- 134 ,(1988) , 10.21236/AD0241531
Yann Lecun, D Touresky, G Hinton, T Sejnowski, A theoretical framework for back-propagation IEEE Computer Society Press. pp. 21- 28 ,(1988)
Irie, Miyake, Capabilities of three-layered perceptrons IEEE 1988 International Conference on Neural Networks. pp. 641- 648 ,(1988) , 10.1109/ICNN.1988.23901
Gallant, White, There exists a neural network that does not make avoidable mistakes IEEE 1988 International Conference on Neural Networks. pp. 657- 664 ,(1988) , 10.1109/ICNN.1988.23903
Ricotti, Ragazzini, Martinelli, Learning of word stress in a sub-optimal second order back-propagation neural network IEEE 1988 International Conference on Neural Networks. pp. 355- 361 ,(1988) , 10.1109/ICNN.1988.23867