High Performance Associative Memories and Structured Weight Dilution

S.P. Turvey, S. Hunt, N. Davey, R. Frank

    Research output: Chapter in Book/Report/Conference proceedingChapter

    36 Downloads (Pure)

    Abstract

    The consequences of two techniques for symmetrically diluting the weights of the standard Hopfield architecture associative memory model, trained using a non-Hebbian learning rule, are examined. This paper reports experimental investigations into the effect of dilution on factors such as: pattern stability and attractor performance. It is concluded that these networks maintain a reasonable level of performance at fairly high dilution rates.
    Original languageEnglish
    Title of host publicationApplications and Science in Soft Computing - Advances in Intelligent and Soft Computing , Vol. 24
    EditorsA. Lotfi, J.M. Garibaldi
    PublisherSpringer Nature
    Pages23-30
    ISBN (Print)978-3-540-40856-7
    Publication statusPublished - 2004

    Keywords

    • Hopfield Networks
    • Basins of Attraction

    Fingerprint

    Dive into the research topics of 'High Performance Associative Memories and Structured Weight Dilution'. Together they form a unique fingerprint.

    Cite this