Probabilistic data modelling with adaptive TAP mean-field theory

M. Opper, Ole Winther

    Research output: Contribution to journalJournal articleResearchpeer-review

    Abstract

    We demonstrate for the case of single-layer neural networks how an extension of the TAP mean-field approach of disorder physics can be applied to the computation of approximate averages in probabilistic models for real data.
    Original languageEnglish
    JournalPhysica a-statistical mechanics and its applications
    Volume302
    Issue number1-4
    Pages (from-to)119-125
    ISSN0378-4371
    Publication statusPublished - 2001

    Cite this