BIROn - Birkbeck Institutional Research Online

    New globally convergent training scheme based on the resilient propagation algorithm

    Anastasiadis, A.D. and Magoulas, George and Vrahatis, M.N. (2005) New globally convergent training scheme based on the resilient propagation algorithm. Neurocomputing 64 , pp. 253-270. ISSN 0925-2312.

    Full text not available from this repository.

    Abstract

    In this paper, a new globally convergent modification of the Resilient Propagation-Rprop algorithm is presented. This new addition to the Rprop family of methods builds on a mathematical framework for the convergence analysis that ensures that the adaptive local learning rates of the Rprop's schedule generate a descent search direction at each iteration. Simulation results in six problems of the PROBEN1 benchmark collection show that the globally convergent modification of the Rprop algorithm exhibits improved learning speed, and compares favorably against the original Rprop and the Improved Rprop, a recently proposed Rrpop modification.

    Metadata

    Item Type: Article
    School: School of Business, Economics & Informatics > Computer Science and Information Systems
    Depositing User: Sarah Hall
    Date Deposited: 22 Jun 2021 12:46
    Last Modified: 22 Jun 2021 12:46
    URI: https://eprints.bbk.ac.uk/id/eprint/44840

    Statistics

    Downloads
    Activity Overview
    0Downloads
    14Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item