Generalization performance of multi-class discriminant models

Hélène Paugam-Moisy André Elisseeff Yann Guermeur 1
1 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Starting from a direct definition of the notion of margin in the multiclass case , we study the generalization performance of multiclass discriminant systems. In the framework of statistical learning theory, we establish on this performance a bound based on covering numbers. An application to a linear ensemble method w hich estimates the class posterior probabilities provides us with a way to compa re this bound and another one based on combinatorial dimensions, with respect to the capacity measure they incorporate. Experimental results highlight their use fulness for a real-world problem.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00099163
Contributor : Publications Loria <>
Submitted on : Tuesday, September 26, 2006 - 8:51:27 AM
Last modification on : Thursday, January 11, 2018 - 6:19:48 AM

Identifiers

  • HAL Id : inria-00099163, version 1

Collections

Citation

Hélène Paugam-Moisy, André Elisseeff, Yann Guermeur. Generalization performance of multi-class discriminant models. IJCNN'2000, 2000, Come, Italie, pp.177-182. ⟨inria-00099163⟩

Share

Metrics

Record views

128