Universal Kernel-Based Learning with Applications to Regular Languages

Abstract

We propose a novel framework for supervised learning of discrete concepts. Since the 1970's, the standard computational primitive has been to find the most consistent hypothesis in a given complexity class. In contrast, in this paper we propose a new basic operation: for each pair of input instances, count how many concepts of bounded complexity contain both of them.

Cite

Text

Kontorovich and Nadler. "Universal Kernel-Based Learning with Applications to Regular Languages." Journal of Machine Learning Research, 2009.

Markdown

[Kontorovich and Nadler. "Universal Kernel-Based Learning with Applications to Regular Languages." Journal of Machine Learning Research, 2009.](https://mlanthology.org/jmlr/2009/kontorovich2009jmlr-universal/)

BibTeX

@article{kontorovich2009jmlr-universal,
  title     = {{Universal Kernel-Based Learning with Applications to Regular Languages}},
  author    = {Kontorovich, Leonid and Nadler, Boaz},
  journal   = {Journal of Machine Learning Research},
  year      = {2009},
  pages     = {1095-1129},
  volume    = {10},
  url       = {https://mlanthology.org/jmlr/2009/kontorovich2009jmlr-universal/}
}