Nonmonotone learning rules for backpropagation networks

Plagianakos, V.P. and Magoulas, George and Vrahatis, M.N. (1999) Nonmonotone learning rules for backpropagation networks. In: UNSPECIFIED (ed.) 6th IEEE International Conference on Electronics, Circuits and Systems. IEEE Computer Society, pp. 291-294. ISBN 0780356829.

Full text not available from this repository.

Official URL: https://doi.org/10.1109/ICECS.1999.812280

Abstract

In this paper we study nonmonotone learning rules, based on an acceptability criterion for the calculated learning rate. More specifically, we impose that the error function value at each epoch must satisfy an Armijo-type criterion, with respect to the maximum error function value of a predetermined number of previous epochs. To test this approach, we propose two training algorithms with adaptive learning rates that employ the above-mentioned acceptability criterion. Experimental results show that the proposed algorithms have considerably improved convergence speed, success rate, and generalization, when compared with other classical neural network training methods.

Metadata

Item Type:	Book Section
School:	Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences
Depositing User:	Sarah Hall
Date Deposited:	06 Jul 2021 12:12
Last Modified:	09 Aug 2023 12:51
URI:	https://eprints.bbk.ac.uk/id/eprint/45004

Statistics

Archive Staff Only (login required)

Edit/View Item