Learning approximately regular languages with reversible languages

Satoshi Kobayashi, Takashi Yokomori

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

In this note, we consider the problem of learning approximately regular languages in the limit from positive data using the class of k-reversible languages. The class of k-reversible languages was introduced by Angluin (1982), and proved to be efficiently identifiable in the limit from positive data only. We show that Angluin's learning algorithm for the class of k-reversible languages can be readily adopted for the approximate identification of regular languages from positive data. Considering the negative result on the exact identifiability by Gold (1967), this approximation approach would be one of the best we could hope for learning the class of regular languages from positive data only.

Original languageEnglish
Pages (from-to)251-257
Number of pages7
JournalTheoretical Computer Science
Volume174
Issue number1-2
Publication statusPublished - 1997 Mar 15
Externally publishedYes

Fingerprint

Formal languages
Regular Languages
Learning algorithms
Identifiability
Gold
Learning Algorithm
Learning
Language
Class
Approximation

Keywords

  • Approximate learning
  • Computational learning theory
  • Formal language theory
  • Identification in the limit

ASJC Scopus subject areas

  • Computational Theory and Mathematics

Cite this

Learning approximately regular languages with reversible languages. / Kobayashi, Satoshi; Yokomori, Takashi.

In: Theoretical Computer Science, Vol. 174, No. 1-2, 15.03.1997, p. 251-257.

Research output: Contribution to journalArticle

@article{28886fcafd114cc79bc1c057a3106418,
title = "Learning approximately regular languages with reversible languages",
abstract = "In this note, we consider the problem of learning approximately regular languages in the limit from positive data using the class of k-reversible languages. The class of k-reversible languages was introduced by Angluin (1982), and proved to be efficiently identifiable in the limit from positive data only. We show that Angluin's learning algorithm for the class of k-reversible languages can be readily adopted for the approximate identification of regular languages from positive data. Considering the negative result on the exact identifiability by Gold (1967), this approximation approach would be one of the best we could hope for learning the class of regular languages from positive data only.",
keywords = "Approximate learning, Computational learning theory, Formal language theory, Identification in the limit",
author = "Satoshi Kobayashi and Takashi Yokomori",
year = "1997",
month = "3",
day = "15",
language = "English",
volume = "174",
pages = "251--257",
journal = "Theoretical Computer Science",
issn = "0304-3975",
publisher = "Elsevier",
number = "1-2",

}

TY - JOUR

T1 - Learning approximately regular languages with reversible languages

AU - Kobayashi, Satoshi

AU - Yokomori, Takashi

PY - 1997/3/15

Y1 - 1997/3/15

N2 - In this note, we consider the problem of learning approximately regular languages in the limit from positive data using the class of k-reversible languages. The class of k-reversible languages was introduced by Angluin (1982), and proved to be efficiently identifiable in the limit from positive data only. We show that Angluin's learning algorithm for the class of k-reversible languages can be readily adopted for the approximate identification of regular languages from positive data. Considering the negative result on the exact identifiability by Gold (1967), this approximation approach would be one of the best we could hope for learning the class of regular languages from positive data only.

AB - In this note, we consider the problem of learning approximately regular languages in the limit from positive data using the class of k-reversible languages. The class of k-reversible languages was introduced by Angluin (1982), and proved to be efficiently identifiable in the limit from positive data only. We show that Angluin's learning algorithm for the class of k-reversible languages can be readily adopted for the approximate identification of regular languages from positive data. Considering the negative result on the exact identifiability by Gold (1967), this approximation approach would be one of the best we could hope for learning the class of regular languages from positive data only.

KW - Approximate learning

KW - Computational learning theory

KW - Formal language theory

KW - Identification in the limit

UR - http://www.scopus.com/inward/record.url?scp=0031097569&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031097569&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0031097569

VL - 174

SP - 251

EP - 257

JO - Theoretical Computer Science

JF - Theoretical Computer Science

SN - 0304-3975

IS - 1-2

ER -