BIROn - Birkbeck Institutional Research Online

    Globally convergent modification of the quickprop method

    Vrahatis, M.N. and Magoulas, George and Plagianakos, V.P. (2000) Globally convergent modification of the quickprop method. Neural Processing Letters 12 (2), pp. 159-170. ISSN 1370-4621.

    Full text not available from this repository.

    Abstract

    A mathematical framework for the convergence analysis of the well-known Quickprop method is described. Furthermore, we propose a modification of this method that exhibits improved convergence speed and stability, and, at the same time, alleviates the use of heuristic learning parameters. Simulations are conducted to compare and evaluate the performance of the new modified Quickprop algorithm with various popular training algorithms. The results of the experiments indicate that the increased convergence rates achieved by the proposed algorithm, affect by no means its generalization capability and stability.

    Metadata

    Item Type: Article
    School: School of Business, Economics & Informatics > Computer Science and Information Systems
    Depositing User: Sarah Hall
    Date Deposited: 06 Jul 2021 11:08
    Last Modified: 06 Jul 2021 11:08
    URI: https://eprints.bbk.ac.uk/id/eprint/44992

    Statistics

    Downloads
    Activity Overview
    0Downloads
    4Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item