Critical vector learning to construct sparse kernel modeling with PRESS statistic

Junbin Gao, Lei Zhang, Daming Shi

    Research output: Book chapter/Published conference paperConference paperpeer-review

    1 Citation (Scopus)
    9 Downloads (Pure)

    Abstract

    A novel critical vector (CV) regression algorithm is proposed in the paper based on our previous work [9] and PRESS statistics. The proposed regularized CV algorithm finds critical vectors in a successive greedy process in which, compared to the classical OLS algorithm, the orthogonalization has been removed from the algorithm. The performance of the proposed algorithm is comparable to the OLS algorithm while it saves a lot of time complexities in implementing orthogonalization needed in the OLS algorithm.
    Original languageEnglish
    Title of host publication3rd International Conference on Machine Learning and Cybernetics 2004
    Place of PublicationUSA
    PublisherIEEE
    Pages3223-3228
    Number of pages6
    Volume5
    ISBN (Electronic)0780384032
    DOIs
    Publication statusPublished - 2004
    EventInternational Conference on Machine Learning and Cybernetics - Shanghai, China, China
    Duration: 26 Aug 200429 Aug 2004

    Conference

    ConferenceInternational Conference on Machine Learning and Cybernetics
    Country/TerritoryChina
    Period26/08/0429/08/04

    Fingerprint

    Dive into the research topics of 'Critical vector learning to construct sparse kernel modeling with PRESS statistic'. Together they form a unique fingerprint.

    Cite this