location: Current position: Home >> Scientific Research >> Paper Publications

Convergence of gradient method with momentum for back-propagation neural networks

Hits:

Indexed by:期刊论文

Date of Publication:2008-07-01

Journal:JOURNAL OF COMPUTATIONAL MATHEMATICS

Included Journals:SCIE

Volume:26

Issue:4

Page Number:613-623

ISSN No.:0254-9409

Key Words:back-propagation (BP) neural networks; gradient method; momentum; convergence

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.

Pre One:Convergence of gradient method for Elman networks

Next One:Boundedness of a Batch Gradient Method with Penalty for Feedforward Nerual Networks