Designing Model Based Classifiers by Emphasizing Soft Targets Articles uri icon

authors

  • EL JELALI, SOUFIANE
  • FIGUEIRAS VIDAL, ANIBAL RAMON
  • LYHYAOUI BEN YAHIA, ABDELOUAHID

publication date

  • June 2009

start page

  • 419

end page

  • 433

issue

  • 4

volume

  • 96

International Standard Serial Number (ISSN)

  • 0169-2968

Electronic International Standard Serial Number (EISSN)

  • 1875-8681

abstract

  • When training machine classifiers, to replace hard classification targets by emphasized soft versions of them helps to reduce the negative effects of using standard cost functions as approximations to misclassification rates. This
    emphasis has the same kind of effect as sample editing methods, that have proved
    to be effective for improving classifiers performance. In this paper, we explore
    the effectiveness of using emphasized soft targets with generative models, such
    as Gaussian MixtureModels (GMM), and Gaussian Processes (GP). The interest of
    using GMMis that they offer advantages such as an easy interpretation and
    straightforward possibilities to deal with missing values. With respect to GP,
    if we use soft targets, we do not need to resort to any complex approximation to
    get a Gaussian Process classifier and, simultaneously, we can obtain the
    advantages provided by the use of an emphasis. Simulation results support the
    usefulness of the proposed approach to get better performance and show a low
    sensitivity to design parameters selection.