English

A Universal Kernel for Learning Regular Languages

Machine Learning 2007-12-07 v1 Discrete Mathematics

Abstract

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\eps-approximation.

Keywords

Cite

@article{arxiv.0712.0840,
  title  = {A Universal Kernel for Learning Regular Languages},
  author = {Leonid and Kontorovich},
  journal= {arXiv preprint arXiv:0712.0840},
  year   = {2007}
}

Comments

7 pages

R2 v1 2026-06-21T09:51:01.017Z