Title :
A new multi-class SVM based on a uniform convergence result
Author :
Guermeur, Yann ; Elisseeff, André ; Paugam-Moisy, Hélène
Author_Institution :
LORIA, Vandoeuvre-les-Nancy, France
Abstract :
We introduce a support vector machine devoted to the approximation of multi-class discriminant functions. Its training procedure consists in minimizing an expression of the guaranteed risk. This bound is significantly tighter than the former ones, which should make the implementation of the structural risk minimization inductive principle in the context of multi-class discrimination better grounded
Keywords :
convergence; function approximation; learning (artificial intelligence); matrix algebra; neural nets; pattern recognition; probability; guaranteed risk; multi-class discriminant functions; multi-class discrimination; structural risk minimization inductive principle; support vector machine; training procedure; uniform convergence result; Convergence; Pattern recognition; Quadratic programming; Risk management; Support vector machines; Upper bound; Virtual colonoscopy;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.860770
