Advertisement

Journal of Computer Science and Technology

, Volume 13, Issue 3, pp 268–278 | Cite as

An efficient multiple predicate learner

  • Zhang Xiaolong
  • Masayuki Numao
Article
  • 27 Downloads

Abstract

In this paper, we examine the issue of learning multiple predicates from given training examples. A proposed MPL-CORE algorithm efficiently induces Horn clauses from examples and background knowledge by employing a single predicate learning module CORE. A fast failure mechanism is also proposed which contributes learning effiency and learnability to the algorithm. MPL-CORE employs background knowledge that can be represented in intensional (Horn clauses) or extensional (ground atoms) forms during its learning process. With the fast failure mechanism, MPL-CORE outperforms previous multiple predicate learning systems in both the computational complexity and learnability.

Keywords

Machine learning inductive logic programming multiple predicate learning shift of bias 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Lavrač N, Džeroski S. Inductive Logic Programming Techniques and Applications. Ellis Horwood, 1994.Google Scholar
  2. [2]
    Quilan J R. Learning logical definitions from relations.Machine Learning, 1990, 5(3): 239–266.Google Scholar
  3. [3]
    Muggleton S H, Feng C. Efficient induction of logic programs. Inductive Logic Programming, Muggleton S (ed.), London, Academic Press, 1992, pp.281–297.Google Scholar
  4. [4]
    Richards B L, Mooney R J. Automated refinement of first-order Horn-clause domain theories.Machine Learning, 1995, 19: 95–131.Google Scholar
  5. [5]
    De Raedt L, Lavrač N, Džeroski S. Multiple predicate learning. InProc. Thirteenth International Joint Conference on Artificial Intelligence San Mateo, CA, Morgan Kaufmann, 1993, pp. 1037–1042.Google Scholar
  6. [6]
    Kijsirikul B, Numao M, Shimura M. Efficient learning of logic programs with non-determinate nondiscriminating literals. InProc. Eighth International Workshop on Machine Learning, San Mateo, CA, Morgan Kaufmann, 1991, pp.417–421.Google Scholar
  7. [7]
    Kijsirikul B, Numao M, Shimura M. Discrimination-based constructive induction of logic programs. InProc. Tenth National Conference on Artificial Intelligence, San Mateo, CA, Morgan Kaufmann, 1992, pp.44–49.Google Scholar
  8. [8]
    Zhang X, Numao M. Efficient multiple predicate learner based on fast failure mechanism. Technical Report 95TR-0022, Dept. of Computer Science, Tokyo Institute of Technology, Tokyo, Japan, 1995.Google Scholar
  9. [9]
    Zhang X, Numao M. An efficient approach for discovering knowledge from multiple databases.Chinese Journal of Advanced Software Research 1998, 5 (1).Google Scholar
  10. [10]
    Leon Sterling, Ehud Shapiro. The Art of Prolog. The MIT Press, 1986.Google Scholar
  11. [11]
    Gordon D F, Desjardins M. Evaluation and selection of biases in machine learning.Machine Learning, 1995, 20: 5–22.Google Scholar
  12. [12]
    Silverstein G, Pazzani M. Relational clichés: Constraining constructive induction during relational learning. InProc. of Eighth International Workshop on Machine Learning, Morgan Kaufmann, 1991, pp.203–207.Google Scholar

Copyright information

© Science Press, Beijing China and Allerton Press Inc. 1998

Authors and Affiliations

  1. 1.Department of Computer ScienceTokyo Institute of TechnologyJapan

Personalised recommendations