BIROn - Birkbeck Institutional Research Online

    A new method in neural network supervised training with imprecision

    Magoulas, George and Vrahatis, M.N. and Androulakis, G.S. (1996) A new method in neural network supervised training with imprecision. In: UNSPECIFIED (ed.) Proceedings of Third International Conference on Electronics, Circuits, and Systems: ICECS 1996. IEEE Computer Society, pp. 287-290. ISBN 078033650X.

    Full text not available from this repository.


    We propose a method that proceeds solely with the minimal information of the error function and gradient which is their algebraic signs and takes minimization steps in each weight direction. This approach seems to be practically useful especially when training is affected by technology imperfections and environmental changes that cause unpredictable deviations of parameter values from the designed configuration. Therefore, it may be difficult or impossible to obtain very precise values for the error function and the gradient of error during training.


    Item Type: Book Section
    School: School of Business, Economics & Informatics > Computer Science and Information Systems
    Depositing User: Sarah Hall
    Date Deposited: 06 Jul 2021 13:55
    Last Modified: 06 Jul 2021 13:55


    Activity Overview
    6 month trend
    6 month trend

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item