Internal measuring models in trained neural networks for parameter estimation from images

Tian-Jin Feng, T.J. Feng, Z. Houkes, Maarten J. Korsten, Lieuwe Jan Spreeuwers

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

    82 Downloads (Pure)

    Abstract

    The internal representations of 'learned' knowledge in neural networks are still poorly understood, even for backpropagation networks. The paper discusses a possible interpretation of learned knowledge of a network trained for parameter estimation from images. The outputs of the hidden layer are the internal components of the output parameters. The input-to-hidden weight maps, functioning as a kind of internal measuring model of the parameter components, include statistical features of the training set and seem to have a clear physical and geometrical meaning
    Original languageEnglish
    Title of host publicationProceedings 4th International Conference on Image Processing and its Applications
    Place of PublicationMaastricht, The Netherlands
    PublisherIEEE
    Pages230-233
    Number of pages4
    ISBN (Print)0-85296-543-5
    Publication statusPublished - 7 Apr 1992
    Event4th International Conference on Image Processing and its Applications 1992 - Maastricht, Netherlands
    Duration: 7 Apr 19929 Apr 1992

    Publication series

    Name
    PublisherIEEE Press

    Conference

    Conference4th International Conference on Image Processing and its Applications 1992
    Country/TerritoryNetherlands
    CityMaastricht
    Period7/04/929/04/92

    Keywords

    • IR-16504
    • METIS-113389

    Fingerprint

    Dive into the research topics of 'Internal measuring models in trained neural networks for parameter estimation from images'. Together they form a unique fingerprint.

    Cite this