A Universal Kernel for Learning Regular Languages

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We give a universal kernel that renders all the regular languages linearly separable. We are not able to compute this kernel efficiently and conjecture that it is intractable, but we do have an efficient $\eps$-approximation.
7 pages

Keywords

Machine Learning, Discrete Mathematics, F.1.1; D.3.1; F.4.3

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/143657

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/0712.0840
 http://arxiv.org/abs/0712.0840
 The 5th International Workshop on Mining and Learning with Graphs, 2007

Collections

arXiv