Refutability and Reliability for Inductive Inference of Recursive Real-Valued Functions

• Hirowatari Eiju

  Department of Business Administration, The University of Kitakyushu

• Hirata Kouichi

  Department of Artificial Intelligence, Kyushu Institute of Technology

• Miyahara Tetsuhiro

  Faculty of Information Sciences, Hiroshima City University

• Arikawa Setsuo

  Department of Informatics, Kyushu University

Abstract

Inductive inference gives us a theoretical model of concept learning from examples. In this paper, we study refutably and reliably inductive inference of recursive real-valued functions. First we introduce the new criteria RealRefEx for refutable inference and RealRelEx for reliable inference. Then, we compare these two criteria with RealEx for identification in the limit, RealFin for learning finitely and RealNum¡ for learning by enumeration that have been already introduced in the previous works, and investigate their interaction. In particular, we show that RealRefEx and RealRelEx are closed under union, as similar as the criteria RefEx and RelEx for inductive inference of recursive functions.

Journal

• IPSJ Digital Courier

  IPSJ Digital Courier 1 141-152, 2005

  Information Processing Society of Japan

Keywords

• General Economics, Econometrics and Finance

Details

• CRID: 1390001205222190208
• NII Article ID: 130000022397
• DOI: 10.2197/ipsjdc.1.141
• ISSN: 13497456
• Web Site: http://www.jstage.jst.go.jp/article/ipsjdc/1/0/1_0_141/_pdf
• Text Lang: en
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
• Abstract License Flag: Disallowed