Improving the convergence of the backpropagation algorithm using learning rate adaptation methods

Magoulas, George and Vrahatis, M.N. and Androulakis, G.S. (1999) Improving the convergence of the backpropagation algorithm using learning rate adaptation methods. Neural Computation 11 (7), pp. 1769-1796. ISSN 0899-7667.

Full text not available from this repository.

Official URL: https://doi.org/10.1162/089976699300016223

Abstract

This article focuses on gradient-based backpropagation algorithms that use either a common adaptive learning rate for all weights or an individual adaptive learning rate for each weight and apply the Goldstein/Armijo line search. The learning-rate adaptation is based on descent techniques and estimates of the local Lipschitz constant that are obtained without additional error function and gradient evaluations. The proposed algorithms improve the backpropagation training in terms of both convergence rate and convergence characteristics, such as stable learning and robustness to oscillations. Simulations are conducted to compare and evaluate the convergence behavior of these gradient-based training algorithms with several popular training methods.

Metadata

Item Type:	Article
School:	Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences
Depositing User:	Sarah Hall
Date Deposited:	06 Jul 2021 11:23
Last Modified:	09 Aug 2023 12:51
URI:	https://eprints.bbk.ac.uk/id/eprint/45002

Statistics

Archive Staff Only (login required)

Edit/View Item