Indefinite Kernel Fisher discriminant

Elzbieta Pekalska, Bernard Haasdonk, Elzbieta Pȩkalska

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


    Indefinite kernels arise in practice, e.g. from problem-specific kernel construction. Therefore, it is necessary to understand the behavior and suitability of classifiers in the corresponding indefinite inner product spaces. In this paper we address the Indefinite Kernel Fisher Discriminant (IKFD). First, we give the geometric interpretation of the Fisher Discriminant in indefinite inner product spaces. We show that IKFD is closely related to the well-known formulation of the traditional Kernel Fisher Discriminant derived for positive definite kernels. Practical implications are that IKFD can be directly applied to indefinite kernels without manipulation of the kernel matrix. Experiments demonstrate the geometrically intuitive classification and enable comparisons to other indefinite kernel classifiers. © 2008 IEEE.
    Original languageEnglish
    Title of host publicationProceedings - International Conference on Pattern Recognition|Proc. Int. Conf. Pattern Recognit.
    Place of PublicationTampa, Florida, USA
    ISBN (Print)9781424421756
    Publication statusPublished - 2008
    Event2008 19th International Conference on Pattern Recognition, ICPR 2008 - Tampa, FL
    Duration: 1 Jul 2008 → …


    Conference2008 19th International Conference on Pattern Recognition, ICPR 2008
    CityTampa, FL
    Period1/07/08 → …
    Internet address


    Dive into the research topics of 'Indefinite Kernel Fisher discriminant'. Together they form a unique fingerprint.

    Cite this