Convergence monitoring in generalized Hebbian learning

Andrew P. Paplinski

    Research output: Contribution to conferencePaper

    1 Citation (Scopus)


    In this paper we discuss monitoring of the convergence of the Generalized Hebbian Learning algorithm which performs Principal Component Analysis, or the Karhunen-Loeve transform. We start with presentation of the details of the internal structure of the algorithm. Next we consider a number of inter-related convergence conditions. Finally, we present example of image coding algorithm in which those conditions are verified.

    Original languageEnglish
    Number of pages5
    Publication statusPublished - 1 Jan 1998
    EventIEEE International Joint Conference on Neural Networks 1998 - Anchorage, United States of America
    Duration: 4 May 19989 May 1998 (Proceedings)


    ConferenceIEEE International Joint Conference on Neural Networks 1998
    Abbreviated titleIJCNN 1998
    CountryUnited States of America
    OtherPublished in the World Congress Computational Intelligence'98 Proceedings of the IJCNN'98, FUZZ-IEEE'98, ICEC'98.
    Internet address

    Cite this