Advertisement

Efficient induction of recursive prolog definitions

  • Riverson Rios
  • Stan Matwin
Learning I: Induction
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1081)

Abstract

The ability to learn recursive definitions is a desirable characteristic of a learner. This paper presents Clam, a system that efficiently learns Prolog purely and left-recursive definitions from small data sets by using inverse implication. A learning curve for Clam shows that the accuracy grows with the increase of both positive and negative examples. We believe our system can be used as a preprocessor for a general-purpose system when few examples are at hand.

Keywords

learning, inductive logic programming 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Aha, D., Lapointe, S., Ling, C. & Matwin, S. (1994a) Learning recursive relations with randomly selected small training sets. In Proc. llth ICML (12–18). New Brunswick, NJGoogle Scholar
  2. Aha, D., Lapointe, S., Ling, C. & Matwin, S. (1994b) Inverting implication with small training sets. In Proc. of the 1994 European Conf. on Machine Learning (31–48). Catania, Italy: Springer-VerlagGoogle Scholar
  3. Chao, L. (1994). Using Argument Binding and Predicate Searching Schemes to Guide Partially Recursive Logic Programs Synthesis from Positive Examples. Master's Thesis. National Tsing-Hua University, ChinaGoogle Scholar
  4. Dolšak, N. & Muggleton, S. (1992). The application of ILP to finite-element mesh design. In Inductive Logic Programming, Edited by S. Muggleton, San Diego, CA: Academic PressGoogle Scholar
  5. Dovey, M. (1995). Analysis of Rachmaninoff's piano performance using Inductive Logic Programming. In Proc. 8th European Conf on Machine Learning. Heraclion, CreteGoogle Scholar
  6. Holte, R. (1995). Personal communicationGoogle Scholar
  7. Idestam-Almquist, P. (1995). Efficient induction of recursive definitions by structural analysis of saturation. In Proc. of the 5th Intl. Workshop on Inductive Logic Programming. Leuven, BelgiumGoogle Scholar
  8. Jorge, A. & Brazdil, P. (1995). Architecture for iterative learning of recursive definitions. In Proc. of the 5th Intl. Workshop on Inductive Logic Programming. Leuven, BelgiumGoogle Scholar
  9. Lapointe, S., Ling, C. & Matwin, S. (1993). Constructive inductive logic programming. In Proc. 13th IJCAI (273–281). Chambéry, France: Morgan KaufmannGoogle Scholar
  10. Lapointe, S., & Matwin, S. (1992). Sub-unification: A tool for efficient induction of recursive programs. In Proc. 9th ICML (273–281). Aberdeen, Scotland: Morgan KaufmannGoogle Scholar
  11. Lavrač, N., Džeroski, S. & Grobelnik, M. (1991). Learning nonrecursive definitions of relations with LINUS. In Proc. Fifth European Working Session on Learning (265–281). Berlin, Germany: Springer VerlagGoogle Scholar
  12. Ling, X. (1991). Inductive learning from good examples, In Proc. of the 12th IJCAI (751–756). Sydney, AustraliaGoogle Scholar
  13. Muggleton, S. (1992). Inverting implication. In Proc. of the 9th European Workshop on Inductive Logic Programming. Vienna, Austria: unpublishedGoogle Scholar
  14. Muggleton, S. (1995). Inverse entailment and Progol. New Generation Computing Journal. MayGoogle Scholar
  15. Muggleton, S. & Feng, C. (1990). Efficient induction of logic programs. In Proc. of the First Intl. Workshop on Algorithmic Learning Theory (368–381). Tokyo, Japan: OhmshaGoogle Scholar
  16. Plotkin, G. (1971). Automatic Methods of Inductive Inference. PhD Thesis. Edinburgh University, Edinburgh, ScotlandGoogle Scholar
  17. Quinlan, J. (1990). Learning logical definitions from relations. Machine Learning 5:239–266, Kluwer AcademicGoogle Scholar
  18. Stahl, I. (1995). The efficiency of bias shift operations in ILP. In Proc. of the 5th Intl. Workshop on Inductive Logic Programming. Leuven, BelgiumGoogle Scholar
  19. Sterling, L. & Shapiro, E. (1994). The Art of Prolog: Advanced Programming Techniques. MIT PressGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Riverson Rios
    • 1
  • Stan Matwin
    • 1
  1. 1.Department of Computer ScienceUniversity of OttawaCanada

Personalised recommendations