On-line learning in multilayer neural networks

David Saad, Sara A. Solla

    Research output: Chapter in Book/Published conference outputChapter


    We present an analytic solution to the problem of on-line gradient-descent learning for two-layer neural networks with an arbitrary number of hidden units in both teacher and student networks. The technique, demonstrated here for the case of adaptive input-to-hidden weights, becomes exact as the dimensionality of the input space increases.
    Original languageEnglish
    Title of host publicationProceedings of the first international conference on mathematics of neural networks : models, algorithms and applications: models, algorithms and applications
    Place of PublicationOxford
    ISBN (Print)0-7923-99331
    Publication statusPublished - 1997

    Bibliographical note

    © Springer Science+Business Media New York 1997


    • algorithm
    • design
    • measurement
    • performance
    • theory
    • verification


    Dive into the research topics of 'On-line learning in multilayer neural networks'. Together they form a unique fingerprint.

    Cite this