Molding the knowledge in modular neural networks

L. Spaanenburg, S. Achterop, Cornelis H. Slump, B.J. van der Zwaag

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

    14 Downloads (Pure)

    Abstract

    Problem description. The learning of monolithic neural networks becomes harder with growing network size. Likewise the knowledge obtained while learning becomes harder to extract. Such disadvantages are caused by a lack of internal structure, that by its presence would reduce the degrees of freedom in evolving to a training target. A suitable internal structure with respect to modular network construction as well as to nodal discrimination is required. Details on the grouping and selection of nodes can sometimes be concluded from the characteristics of the application area; otherwise a comprehensive search within the solution space is necessary.
    Original languageUndefined
    Title of host publicationLearning Solutions
    Place of PublicationNetherlands
    PublisherSTW
    Pages25-26
    Number of pages2
    Publication statusPublished - Jun 2002
    EventLerende Oplossingen: Lerende Oplossingen - Nijmegen, Netherlands
    Duration: 14 Jun 200214 Jun 2002

    Publication series

    Name
    PublisherTechnologiestichting STW

    Seminar

    SeminarLerende Oplossingen
    CountryNetherlands
    CityNijmegen
    Period14/06/0214/06/02

    Keywords

    • EWI-1418
    • METIS-206439
    • IR-43372

    Cite this