open access

https://hdl.handle.net/2115/87290

On the amount of nonconstructivity in learning formal languages from text

英語

Formal languages

2020-11

Elsevier

Information and computation

281

104668

Nonconstructive computations by various types of machines and automata have been considered by, for example, Karp and Lipton as well as Freivalds. They allow to regard more complicated algorithms from the viewpoint of much more primitive computational devices. The amount of nonconstructivity is a quantitative characterization of the distance between types of computational devices with respect to solving a specific problem. This paper studies the amount of nonconstructivity needed to learn classes of formal languages. Different learning types are compared with respect to the amount of nonconstructivity needed to learn indexable classes and recursively enumerable classes, respectively, of formal languages from positive data. Matching upper and lower bounds for the amount of nonconstructivity needed are shown. (C) 2020 Elsevier Inc. All rights reserved.

学術雑誌論文

Accepted Manuscript

Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

©2021. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/

0890-5401

1090-2651

AA1067013X