Preparing for knowledge extraction in modular neural networks

Lambert Spaanenburg, Cornelis H. Slump, Rienk Venema, B.J. van der Zwaag

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    23 Downloads (Pure)

    Abstract

    Neural networks learn knowledge from data. For a monolithic structure, this knowledge can be easily used but not isolated. The many degrees of freedom while learning make knowledge extraction a computationally intensive process as the representation is not unique. Where existing knowledge is inserted to initialize the network for training, the effect becomes subsequently randomized within the solution space. The paper describes structuring techniques such as modularity and hierarchy to create a topology that provides a better view on the learned knowledge to support a later rule extraction.
    Original languageUndefined
    Title of host publication3rd IEEE Benelux Signal Processing Symposium (SPS-2002)
    Place of PublicationLeuven, Belgium
    PublisherKatholieke Universiteit
    Pages121-124
    Number of pages4
    ISBN (Print)-
    Publication statusPublished - Mar 2002
    Event3rd IEEE Benelux Signal Processing Symposium, SPS-2002 - Leuven, Belgium
    Duration: 21 Mar 200222 Mar 2002
    Conference number: 3

    Conference

    Conference3rd IEEE Benelux Signal Processing Symposium, SPS-2002
    Abbreviated titleSPS
    CountryBelgium
    CityLeuven
    Period21/03/0222/03/02

    Keywords

    • EWI-1438
    • IR-43136
    • METIS-205958

    Cite this