On the Classification of Recursive Languages

Authors

John Case, University of DelawareFollow
Efim Kinber, Sacred Heart UniversityFollow
Arun Sharma, University of New South Wales
Stephen Frank, University of New South Wales

Document Type

Article

Publication Date

7-2004

Abstract

A one-sided classifier for a given class of languages converges to 1 on every language from the class and outputs 0 infinitely often on languages outside the class. A two-sided classifier, on the other hand, converges to 1 on languages from the class and converges to 0 on languages outside the class. The present paper investigates one-sided and two-sided classification for classes of recursive languages. Theorems are presented that help assess the classifiability of natural classes. The relationships of classification to inductive learning theory and to structural complexity theory in terms of Turing degrees are studied. Furthermore, the special case of classification from only positive data is also investigated.

Comments

Published: Case, John et al. "On the Classification of Recursive Languages." Information and Computation 192.1 (2004): 15-40.

DOI

10.1016/j.ic.2004.03.001

Recommended Citation

Case, John et al. "On the Classification of Recursive Languages." Information and Computation 192.1 (2004): 15-40.