Precision requirements for single-layer feed-forward neural networks

Anne J. Annema, K. Hoen, Klaas Hoen, Hans Wallinga

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

    21 Citations (Scopus)
    88 Downloads (Pure)

    Abstract

    This paper presents a mathematical analysis of the effect of limited precision analog hardware for weight adaptation to be used in on-chip learning feedforward neural networks. Easy-to-read equations and simple worst-case estimations for the maximum tolerable imprecision are presented. As an application of the analysis, a worst-case estimation on the minimum size of the weight storage capacitors is presented
    Original languageEnglish
    Title of host publicationProceedings of the Fourth International Conference on Microelectronics for Neural Networks and Fuzzy Systems, 1994
    Place of PublicationPiscataway, NJ, USA
    PublisherIEEE
    Pages-
    ISBN (Print)9780818667107
    DOIs
    Publication statusPublished - 1994
    Event4th International Conference on Microelectronics for Neural Networks and Fuzzy Systems, ICMNN 1994 - Turin, Italy
    Duration: 26 Sep 199428 Sep 1994
    Conference number: 4

    Publication series

    Name
    PublisherIEEE
    Volume145

    Conference

    Conference4th International Conference on Microelectronics for Neural Networks and Fuzzy Systems, ICMNN 1994
    Abbreviated titleICMNN
    CountryItaly
    CityTurin
    Period26/09/9428/09/94

    Keywords

    • IR-56029
    • METIS-310955

    Fingerprint Dive into the research topics of 'Precision requirements for single-layer feed-forward neural networks'. Together they form a unique fingerprint.

    Cite this