ϵ-sparse representations : generalized sparse approximation and the equivalent family of SVM tasks

Szabó, Zoltán and Lőrincz, András: ϵ-sparse representations : generalized sparse approximation and the equivalent family of SVM tasks. Acta cybernetica, (17) 3. pp. 605-614. (2006)

[img] Cikk, tanulmány, mű
Lorincz_2006_ActaCybernetica.pdf

Download (138kB)

Abstract

Relation between a family of generalized Support Vector Machine (SVM) problems and the novel ϵ-sparse representation is provided. In defining ϵ-sparse representations, we use a natural generalization of the classical ϵ-insensitive cost function for vectors. The insensitive parameter of the SVM problem is transformed into component-wise insensitivity and thus overall sparsification is replaced by component-wise sparsification. The connection between these two problems is built through the generalized Moore-Penrose inverse of the Gram matrix associated to the kernel.

Item Type: Article
Journal or Publication Title: Acta cybernetica
Date: 2006
Volume: 17
Number: 3
Page Range: pp. 605-614
ISSN: 0324-721X
Language: angol
Uncontrolled Keywords: Természettudomány, Informatika
Additional Information: Bibliogr.: p. 613-614.; Abstract
Date Deposited: 2016. Oct. 15. 12:25
Last Modified: 2018. Jun. 05. 15:14
URI: http://acta.bibl.u-szeged.hu/id/eprint/12784

Actions (login required)

View Item View Item