Limited Weights Neural Networks - Very Tight Entropy Based Bounds

Valeriu Beiu, Sorin Draghici

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Being given a set of m examples (i.e., data-set) from IR{sup n} belonging to k different classes, the problem is to compute the required number-of-bits (i.e., entropy) for correctly classifying the data-set. Very tight upper and lower bounds for a dichotomy (i.e., k = 2) will be presented, but they are valid for the general case.
    Original languageEnglish
    Title of host publicationICSC International Symposium on Soft Computing
    PublisherMillet : ICSC Academic Press
    Publication statusPublished - Dec 31 1997
    EventSOCO'97 - Nîmes, France
    Duration: Sept 17 1997 → …

    Conference

    ConferenceSOCO'97
    Period9/17/97 → …

    Fingerprint

    Dive into the research topics of 'Limited Weights Neural Networks - Very Tight Entropy Based Bounds'. Together they form a unique fingerprint.

    Cite this