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

1996 Fiscal Year Final Research Report Summary

Study on Inductive Learning Based on Positive Examples

Research Project

Project/Area Number 07680406
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeSingle-year Grants
Section一般
Research Field Intelligent informatics
Research InstitutionKyushu Institute of Technology

Principal Investigator

SHINOHARA Takeshi  Kyushu Institute of Technology, Department of Atrificial Intelligence, Professor, 情報工学部, 教授 (60154225)

Project Period (FY) 1995 – 1996
KeywordsInductive Inference / Machine Learning / Learning from Positive Examples / Pattern Languages / Elementary Formal Systems / Efficiency of Learning
Research Abstract

A pattern is a string consisting of constant symbols and variables. The language of a pattern is the set of constant strings obtained by substituting nonempty constant strings for variables in the pattern. For any fixed k, the class of unions of at most k pattern languages is already shown to be inferable from positive data.
We apply a learning algorithm for pattern languages to discover a motif from amino-acid sequences. From only positive examples with the help of an alphsbet indexing, the algorithm succesfully finds sets of patterns, that can be considered as motifs.
The class of all the unions of arbitrarily finitely many pattern languages in not inferable, because any constant string defines a singleton set consisting of itself, and the class of unions contains all the finite languages. A proper pattern is a pattern that contains at least one variable. The language of a proper pattern is infinite. In this paper, we consider the class of unions when patterns are restricted to be priper and show that the class is not inferable from positive data. When patterns are restricted not to contain more than l consecutive occurrences of constant symbols for some l, the class of unions is shown to be inferable from positive data.

  • Research Products

    (12 results)

All Other

All Publications (12 results)

  • [Publications] H.Arimura,T.Shinohara: "Logical generalization for learning with background knowledge" ICLP'95 Post-Conference Workshop on Inductive Logic Programming,IA-TR-95-03. 1-11 (1995)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] H.Arimura,H.Ishizaka,T.Shinohara: "Learning nuions of tree patterns using queries" Proc.the 6th International Workshop on Algorithmic Learning Theory (Lecture Notes in Artificial Intelligence). 997. 66-79 (1995)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 山口美千代,篠原武,ほか: "複数文字列パターンによるアミノ酸配列からのタンパク質モティーフの発見" 情報処理学会研究報告,情報学基礎No.38. 33-40 (1995)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] 遠里由佳子,有村博紀,篠原武: "概念階層を持つパターン言語の学習可能性" 情報基礎論ワークショップ(LAシンポジウム). (1996)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] T.Shinohara,H.Arimura: "Inductive inference of unbounded unions of pattern languages from positive data" Proc.the 7th International Workshop on Algorithmic Learning Theory (Lecture Notes in Artificial Intelligence). 1160. 256-271 (1996)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] M.Yamaguchi,S.Shimozono,T.Shinohara: "Finding minimal generalization over regular patterns with alphabet indexing" Proc.the 7th Workshop on Genome Informatics. 51-60 (1996)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] K.P.Jantke,T.Shinohara,T.Zeugmann (Eds.): "Algorithmic Learning Theory" Springer-Verlag, 319 (1995)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] H.Arimura, T.Shinohara: "Logical generalization for learning with background knowledge" ICLP'95 Post-Conference Workshop on Inductive Logic Programming. IATR-95-03. 1-11 (1995)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] H.Arimura, H.Ishizaka, T.Shinohara: "Learning unions of tree patterns using queries" Proc.the 6th International Workshop on Algorithmic Learning Theory (Lecture Notes in Artificial Intelligence 997). 66-271 (1995)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] T.Shinohara, H.Arimura: "Inductive inference of unbounded unions of pattern languages from positive data" Proc.the 7th International Workshop on Algorithmic Learning Theory (Lecture Notes in Artificial Intelligence 1160). 256-271 (1996)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] M.Yamaguchi, S.Shimozono, T.Shinohara: "Finding minimal generalization over regular patterns with alphabet indexing" Proc.the 7th Workshop on Genome Informatics. 51-60 (1996)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] K.P.Jantke, T.Shinohara, T.Zeugmann (Eds.): "Algorithmic Learning Theory" (Lecture Notes in Artificial Intelligence 997) Springer-Verlag. 319 (1995)

    • Description
      「研究成果報告書概要(欧文)」より

URL: 

Published: 1999-03-09  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi