International Conference on Algorithmic Learning Theory

ALT 2005: Algorithmic Learning Theory pp 269-282

Inferring Unions of the Pattern Languages by the Most Fitting Covers

  • Yen Kaow Ng
  • Takeshi Shinohara
Conference paper

DOI: 10.1007/11564089_22

Volume 3734 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Ng Y.K., Shinohara T. (2005) Inferring Unions of the Pattern Languages by the Most Fitting Covers. In: Jain S., Simon H.U., Tomita E. (eds) Algorithmic Learning Theory. ALT 2005. Lecture Notes in Computer Science, vol 3734. Springer, Berlin, Heidelberg

Abstract

We are interested in learning unions of the pattern languages in the limit from positive data using strategies that guarantee some form of minimality during the learning process. It is known that for any class of languages with so-called finite elasticity, any learning strategy that finds a language that is minimal with respect to inclusion (MINL) ensures identification in the limit. We consider a learning strategy via another form of minimality — the minimality in the number of elements that are shorter than a specified length. A search for languages with this minimality is possible in many cases, and the search can be adapted to identify any class where every language in the class has a characteristic set within the class. We compare solutions using this strategy to those from MINL to illustrate how we may obtain solutions that fulfill both notions of minimality. Finally, we show how the results are relevant using some subclasses of the pattern languages.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Yen Kaow Ng
    • 1
  • Takeshi Shinohara
    • 2
  1. 1.Graduate School of Computer Science and SystemsKyushu Institute of TechnologyIizukaJapan
  2. 2.Department of Artificial IntelligenceKyushu Institute of TechnologyIizukaJapan