Acceleration of backpropagation learning using optimised learning rate and momentum
作者： X-H Yu , None
DOI: 10.1049/EL:19930860
关键词: Estimation theory 、 Simulation 、 Computer science 、 Algorithm 、 Artificial neural network 、 Optimal estimation 、 Acceleration (differential geometry) 、 Backpropagation 、 Momentum (technical analysis)
摘要: Learning rate and momentum factor are two arbitrary parameters that have to be carefully chosen in the conventional backpropagation (BP) learning algorithm. Based on a linear expansion of actual outputs BP network with respect parameters, Letter presents an efficient approach determine dynamically optimal values these parameters. Simulation results indicate present can provide remarkable improvement convergence performance.
harvard.edu
sci-hub.se 参考文章(2)
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
D.R. Hush, B.G. Horne, Progress in supervised neural networks IEEE Signal Processing Magazine. ,vol. 10, pp. 8- 39 ,(1993) , 10.1109/79.180705