• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

INDUCTIVE LEARNING OF DESISION TREES OVER REGULAR PATTERNS AND REGULAR FORMAL SYSTEMS

Research Project

Project/Area Number 15500093
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeSingle-year Grants
Section一般
Research Field Intelligent informatics
Research InstitutionOSAKA PREFECTURE UNIVERSITY

Principal Investigator

SATO Masako  Osaka Prefecture University, College of Integrated Arts and Sciences, Professor, 総合科学部, 教授 (50081419)

Co-Investigator(Kenkyū-buntansha) MUKOUCHI Yasuhito  Osaka Prefecture University, College of Integrated Arts and Sciences, Assistant Professor, 総合科学部, 助教授 (00264820)
Project Period (FY) 2003 – 2004
Project Status Completed (Fiscal Year 2004)
Budget Amount *help
¥2,100,000 (Direct Cost: ¥2,100,000)
Fiscal Year 2004: ¥900,000 (Direct Cost: ¥900,000)
Fiscal Year 2003: ¥1,200,000 (Direct Cost: ¥1,200,000)
KeywordsInductive Inference / Identification in the limit / Elementary Formal System / Positive Examples / Regular Languages / Pattern Languages / SH Systems / Learnability / 帰納学習 / 決定木 / ゲノム情報
Research Abstract

The purpose of this research is to construct fundamental theory of inductive learnability of Elementary Formal Systems(EFSs, for short) allowing erasing substitutions from positive examples. We have obtained the following results :
1.The language defined by the so-called Primitive Formal System(PFS, for short), which consists of a base clause and an induction clause, was shown to be expressed as a union of infinitely many regular pattern languages.
2.We obtained a necessary and sufficient condition for a PFS to be reduced. Moreover, we showed that it is efficiently decidable.
3.The inclusion problem of languages defined by reduced PFSs can he reduced to the syntactical inclusion problem of regular patterns appearing in the original PFSs.
4.We showed that there exists a finite tell-tale set of each language defined by a PFS. Moreover, we showed that the language class defined by PFSs have the property of the so-called M-finite thickness.
5.The class of languages defined by the so-called simp … More le formal systems(SFSs, for short) and regular formal systems(RFSs, for short), which are more general EFSs than PFSs, with at most k axioms is shown to be learnable in case erasing substitutions are not allowed (Shinohara 95). In this research, we showed that the above class is not learnable in case erasing substitutions are allowed.
6.Although PFSs are RFSs with just two axioms, we introduced other syntactical conditions on PFSs and showed that they are learnable from positive examples.
7.We applied the results as mentioned at 6 to the learning problem of languages generated by SH systems. An SH system is a simplified model for expressing a recombinant behavior or a splicing operation for a DNA sequence. The language generated by an SH system is a regular language with some special properties. In this research, we expressed SH languages by RFSs with empty substitutions and showed that they are learnable from positive examples by using results obtained at 6.
8.The languages defined by decision trees over regular patterns were shown to be expressed as finitely many unions and intersections of regular pattern languages and co-regular pattern languages. In this research, we showed that the language class of finitely many unions or intersections of regular pattern languages has the so-called finite elasticity and showed that the class is learnable. The problem for co-regular pattern languages is still open. Less

Report

(3 results)
  • 2004 Annual Research Report   Final Research Report Summary
  • 2003 Annual Research Report
  • Research Products

    (14 results)

All 2004 2003 Other

All Journal Article (11 results) Publications (3 results)

  • [Journal Article] Learning Languages Generated by Elementary Formal Systems and Its Application to SH Languages2004

    • Author(s)
      Yasuhito Mukouchi, Masako Sato
    • Journal Title

      Lecture Notes in Artificial Intelligence 3244

      Pages: 380-394

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2004 Final Research Report Summary
  • [Journal Article] Properties of SH Systems and Their Languages2004

    • Author(s)
      Yasuhito Mukouchi, Rie Takaishi, Masako Sato
    • Journal Title

      Tamsui Oxford Journal of Mathematical Sciences 20

      Pages: 339-352

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2004 Final Research Report Summary
  • [Journal Article] Properties of SH Systems and Their Languages2004

    • Author(s)
      Yasuhito Mukouchi, Rie Takaishi, Masako Sato
    • Journal Title

      Tamsui Oxford Journal of Mathematical Sciences 20(2)

      Pages: 339-352

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2004 Final Research Report Summary
  • [Journal Article] Learning Languages Generated by Elementary Formal Systems and its Application to SH Languages2004

    • Author(s)
      Yasuhito Mukouchi, Masako Sato
    • Journal Title

      Lecture Notes in Artificial Intelligence 3244

      Pages: 389-394

    • Related Report
      2004 Annual Research Report
  • [Journal Article] Properties of SH Systems and Their Languages2004

    • Author(s)
      Yasuhito Mukouchi, Rie Takaishi, Masako Sato
    • Journal Title

      Tamsui Oxford Journal of Mathematical Sciences 20・2

      Pages: 339-352

    • Related Report
      2004 Annual Research Report
  • [Journal Article] Refutable Language Learning with a Neighbor System2003

    • Author(s)
      Yasuhito Mukouchi, Masako Sato
    • Journal Title

      Theoretical Computer Science 298

      Pages: 89-110

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2004 Final Research Report Summary
  • [Journal Article] Learning of Languages Generated by Patterns from Positive Examples2003

    • Author(s)
      Masako Sato, Yasuhito Mukouchi
    • Journal Title

      Scientiae Mathematicae Japonicae 8

      Pages: 479-485

    • NAID

      10012511692

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2004 Final Research Report Summary
  • [Journal Article] Learning of Erasing Primitive Formal Systems from Positive Examples2003

    • Author(s)
      Jin Uemura, Masako Sato
    • Journal Title

      Lecture Notes in Artificial Intelligence 2842

      Pages: 69-83

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2004 Final Research Report Summary
  • [Journal Article] Learning of erasing primitive formal systems from positive examples

    • Author(s)
      Jin Uemura, Masako Sato
    • Journal Title

      Theoretical Computer Science (印刷中)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2004 Final Research Report Summary
  • [Journal Article] Learning of erasing primitive formal systems from positive examples

    • Author(s)
      Jin Uemura, Masako Sato
    • Journal Title

      Theoretical Computer Science (to appear)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2004 Final Research Report Summary
  • [Journal Article] Learning of erasing primitive formal systems from positive examples

    • Author(s)
      Jin, Uemura, Masako Sato
    • Journal Title

      Theoretical Computer Science (to appear)(印刷中)

    • Related Report
      2004 Annual Research Report
  • [Publications] Jin Uemura, Masako Sato: "Learning of Erasing Primitive Formal Systems from Positive Examples"Lecture Notes in Aritificial Intelligence. 2842. 69-83 (2003)

    • Related Report
      2003 Annual Research Report
  • [Publications] Yasuhito Mukouchi, Masako Sato: "Refutable Language Learning with a Neighbor System"Theoretical Computer Science. 298. 89-110 (2003)

    • Related Report
      2003 Annual Research Report
  • [Publications] Masako Sato, Yasuhito Mukouchi: "Learning of Languages Generated by Patterns from Positive Examples"Scientiae Mathematicae Japonicae. 8. 479-485 (2003)

    • Related Report
      2003 Annual Research Report

URL: 

Published: 2003-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi