Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Kernel classifier construction using orthogonal forward selection and boosting with Fisher ratio class separability

S Chen, X X Wang, X Hong

    IEEE Transactions on Neural Networks
    |November 30, 2006
    PubMed
    Summary

    This study introduces a greedy method for building efficient kernel classifiers. The technique optimizes kernel parameters to improve class separability and generalization in Gaussian radial basis function networks.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Case series: 2q33.1 microdeletion syndrome--further delineation of the phenotype.

    Journal of medical genetics·2011
    Same author

    Clinical laboratory practices for the detection of rotavirus in England and Wales: can surveillance based on routine laboratory testing data be used to evaluate the impact of vaccination?

    Euro surveillance : bulletin Europeen sur les maladies transmissibles = European communicable disease bulletin·2009
    Same author

    Fuzzy local linearization and local basis function expansion in nonlinear system modeling.

    IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008
    Same author

    Linearization and state estimation of unknown discrete-time nonlinear dynamic systems using recurrent neurofuzzy networks.

    IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008
    Same author

    Generalized neurofuzzy network modeling algorithms using Bézier-Bernstein polynomial functions and additive decomposition.

    IEEE transactions on neural networks·2008
    Same author

    The relevance vector machine technique for channel equalization application.

    IEEE transactions on neural networks·2008

    Area of Science:

    • Machine Learning
    • Pattern Recognition
    • Computational Statistics

    Background:

    • Kernel classification methods often fix kernel parameters, limiting adaptability.
    • Existing approaches may restrict kernel means to training data.
    • Common variance is often assumed across all kernel terms.

    Discussion:

    • A novel greedy technique constructs parsimonious kernel classifiers.
    • Employs orthogonal forward selection and Fisher ratio for class separability.
    • Tunes individual kernel mean vectors and diagonal covariance matrices.
    • An efficient weighted optimization method based on boosting is developed.

    Key Insights:

    • The proposed method incrementally maximizes Fisher ratio for enhanced class separability.

    Related Experiment Videos

  • It offers a viable alternative to current state-of-the-art kernel modeling.
  • Successfully constructs sparse Gaussian radial basis function network classifiers.

    • Outlook:

    • Potential for improved performance in complex classification tasks.
    • Further research into adaptive kernel parameter optimization.
    • Application in diverse areas requiring robust pattern recognition.