Generalization performance of support vector classifiers for density level detection

Hong Chen

doi:10.1016/j.neucom.2013.03.014

Generalization performance of support vector classifiers for density level detection

2013-11-01

1

PRE

AI

DOI：10.1016/j.neucom.2013.03.014

Original

Original request for help

Save

Abstract

En 中文

This paper investigates the generalization performance of support vector classifiers for density level detection (DLD) when the input term belongs to a separable Hilbert space. The estimate of learning rate for OLD problem is established by Rademacher average and iterative techniques, which is independent of the assumption of covering number used in the previous literature. (C) 2013 Elsevier B.V. All rights reserved.

Keywords:

Learning rate

Density level detection

Rademacher average

Iterative technique

Generalization performance of support vector classifiers for density level detection

Abstract

Journal

Organization