2011 | OriginalPaper | Buchkapitel
Incorporating a Priori Knowledge from Detractor Points into Support Vector Classification
verfasst von : Marcin Orchel
Erschienen in: Adaptive and Natural Computing Algorithms
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
In this article, we extend the idea of a priori knowledge in the form of detractor points presented recently for Support Vector Classification. We show that detractor points can belong to the new type of support vectors – training samples which lie outside a margin bounded region. We present the new application for a priori knowledge from detractor points – improving generalization performance of Support Vector Classification while reducing a complexity of a model by removing a bunch of support vectors. The experiments show that indeed the new type of a priori knowledge improves generalization performance of reduced models. The tests were performed on selected classification data sets, and on stock price data from public domain repositories.