Candidate elimination criteria for Lazy Bayesian Rules

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

    10 Citations (Scopus)

    Abstract

    Lazy Bayesian Rules modifies naive Bayesian classification to undo elements of the harmful attribute independence assumption. It has been shown to provide classification error comparable to boosting decision trees. This paper explores alternatives to the candidate elimination criterion employed within Lazy Bayesian Rules. Improvements over naive Bayes are consistent so long as the candidate elimination criteria ensures there is sufficient data for accurate probability estimation. However, the original candidate elimination criterion is demonstrated to provide better overall error reduction than the use of a minimum data subset size criterion.
    Original languageEnglish
    Title of host publicationAI 2001: Advances in Artificial Intelligence
    Subtitle of host publication14th Australian Joint Conference on Artificial Intelligence Adelaide, Australia, December 10-14, 2001 Proceedings
    EditorsMarkus Stumptner, Dan Corbett, Mike Brooks
    Place of PublicationBerlin Germany
    PublisherSpringer
    Pages545-556
    Number of pages12
    ISBN (Print)3540429603
    DOIs
    Publication statusPublished - 2001
    EventAustralasian Joint Conference on Artificial Intelligence 2001 - Adelaide, Australia
    Duration: 10 Dec 200114 Dec 2001
    Conference number: 14th
    https://link.springer.com/book/10.1007/3-540-45656-2 (Proceedings)

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer
    Volume2256
    ISSN (Print)0302-9743

    Conference

    ConferenceAustralasian Joint Conference on Artificial Intelligence 2001
    Abbreviated titleAI 2001
    Country/TerritoryAustralia
    CityAdelaide
    Period10/12/0114/12/01
    Internet address

    Cite this