Year: 2008
Journal of Computational Mathematics, Vol. 26 (2008), Iss. 4 : pp. 613–623
Abstract
In this work, a gradient method with momentum for BP neural networks is considered. The momentum coefficient is chosen in an adaptive manner to accelerate and stabilize the learning procedure of the network weights. Corresponding convergence results are proved.
You do not have full access to this article.
Already a Subscriber? Sign in as an individual or via your institution
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/2008-JCM-8645
Journal of Computational Mathematics, Vol. 26 (2008), Iss. 4 : pp. 613–623
Published online: 2008-01
AMS Subject Headings:
Copyright: COPYRIGHT: © Global Science Press
Pages: 11
Keywords: Back-propagation (BP) neural networks Gradient method Momentum Convergence.