Nonmonotone methods for backpropagation training with adaptive learning rate

Palgianakos, V.P. and Vrahatis, M.N. and Magoulas, George (1999) Nonmonotone methods for backpropagation training with adaptive learning rate. In: UNSPECIFIED (ed.) International Joint Conference Neural Networks: IJCNN 1999. IEEE Computer Society, pp. 1762-1767. ISBN 0780355296.

Full text not available from this repository.

Official URL: https://doi.org/10.1109/IJCNN.1999.832644

Abstract

We present nonmonotone methods for feedforward neural network training, i.e., training methods in which error function values are allowed to increase at some iterations. More specifically, at each epoch we impose that the current error function value must satisfy an Armijo-type criterion, with respect to the maximum error function value of M previous epochs. A strategy to dynamically adapt M is suggested and two training algorithms with adaptive learning rates that successfully employ the above mentioned acceptability criterion are proposed. Experimental results show that the nonmonotone learning strategy improves the convergence speed and the success rate of the methods considered.

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 13:27
Last Modified:	09 Aug 2023 12:51
URI:	https://eprints.bbk.ac.uk/id/eprint/45008

Statistics

Archive Staff Only (login required)