BIROn - Birkbeck Institutional Research Online

    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.

    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: School of Business, Economics & Informatics > Computer Science and Information Systems
    Depositing User: Sarah Hall
    Date Deposited: 06 Jul 2021 11:23
    Last Modified: 06 Jul 2021 11:23
    URI: https://eprints.bbk.ac.uk/id/eprint/45002

    Statistics

    Downloads
    Activity Overview
    0Downloads
    5Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item