Advertisement

Learning Range Restricted Horn Expressions

  • Roni Khardon
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1572)

Abstract

We study the learnability of first order Horn expressions from equivalence and membership queries. We show that the class of range restricted Horn expressions, where every term in the consequent of every clause appears also in the antecedent of the clause, is learnable. The result holds both for the model where interpretations are examples (learning from interpretations) and the model where clauses are examples (learning from entailment).

The paper utilises a previous result on learning function free Horn expressions. This is done by using techniques for flattening and unflattening of examples and clauses, and a procedure for model finding for range restricted expressions. This procedure can also be used to solve the implication problem for this class.

Keywords

Logic Program Function Symbol Inductive Logic Inductive Logic Programming Horn Clause 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. AFP92.
    D. Angluin, M. Frazier, and L. Pitt. Learning conjunctions of Horn clauses. Machine Learning, 9:147–164, 1992.zbMATHGoogle Scholar
  2. AK95.
    D. Angluin and M. Kharitonov. When won’t membership queries help? Journal of Computer and System Sciences, 50:336–355, 1995.zbMATHCrossRefMathSciNetGoogle Scholar
  3. Ang88.
    D. Angluin. Queries and concept learning. Machine Learning, 2(4):319–342, 1988.Google Scholar
  4. Ari97.
    H. Arimura. Learning acyclic first-order Horn sentences from entailment. In Proceedings of the International Conference on Algorithmic Learning Theory. Springer-verlag, 1997. LNAI 1316.Google Scholar
  5. CK90.
    C. Chang and J. Keisler. Model Theory. Elsevier, Amsterdam, Holland, 1990.zbMATHCrossRefGoogle Scholar
  6. Coh95a.
    W. Cohen. PAC-learning recursive logic programs: Efficient algorithms. Journal of Artificial Intelligence Research, 2:501–539, 1995.zbMATHGoogle Scholar
  7. Coh95b.
    W. Cohen. PAC-learning recursive logic programs: Negative result. Journal of Artificial Intelligence Research, 2:541–573, 1995.zbMATHGoogle Scholar
  8. DR97.
    L. De Raedt. Logical settings for concept learning. Artificial Intelligence, 95(1):187–201, 1997. See also relevant Errata.zbMATHCrossRefMathSciNetGoogle Scholar
  9. DRB92.
    L. De Raedt and M. Bruynooghe. An overview of the interactive concept learner and theory revisor CLINT. In S. Muggleton, editor, Inductive Logic Programming. Academic Press, 1992.Google Scholar
  10. DRD94.
    L. De Raedt and S. Dzeroski. First order jk-clausal theories are PAC-learnable. Artificial Intelligence, 70:375–392, 1994.zbMATHCrossRefMathSciNetGoogle Scholar
  11. FP93.
    M. Frazier and L. Pitt. Learning from entailment: An application to propositional Horn sentences. In Proceedings of the International Conference on Machine Learning, pages 120–127, Amherst, MA, 1993. Morgan Kaufmann.Google Scholar
  12. Hau89.
    D. Haussler. Learning conjunctive concepts in structural domains. Machine Learning, 4(1):7–40, 1989.MathSciNetGoogle Scholar
  13. Kha96.
    R. Khardon. Learning to take actions. In Proceedings of the National Conference on Artificial Intelligence, pages 787–792, Portland, Oregon, 1996. AAAI Press.Google Scholar
  14. Kha98.
    R. Khardon. Learning function free Horn expressions. Technical Report ECS-LFCS-98-394, Laboratory for Foundations of Computer Science, Edinburgh University, 1998. A preliminary version of this paper appeared in COLT 1998.Google Scholar
  15. Lit88.
    N. Littlestone. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2:285–318, 1988.Google Scholar
  16. Llo87.
    J.W. Lloyd. Foundations of Logic Programming. Springer Verlag, 1987. Second Edition.Google Scholar
  17. MB92.
    S. Muggleton and W. Buntine. Machine invention of first order predicates by inverting resolution. In S. Muggleton, editor, Inductive Logic Programming. Academic Press, 1992.Google Scholar
  18. MDR94.
    S. Muggleton and L. De Raedt. Inductive logic programming: Theory andmethods. Journal of Logic Programming, 20:629–679, 1994.CrossRefGoogle Scholar
  19. MF92.
    S. Muggleton and C. Feng. Efficient induction of logic programs. In S. Muggleton, editor, Inductive Logic Programming. Academic Press, 1992.Google Scholar
  20. Min88.
    J. Minker, editor. Foundations of Deductive Databases and Logic Programming. Morgan Kaufmann, 1988.Google Scholar
  21. NCDW97.
    S. Nienhuys-Cheng and R. De Wolf. Foundations of Inductive Logic Programming. Springer-verlag, 1997. LNAI 1228.Google Scholar
  22. Plo70.
    G.D. Plotkin. A note on inductive generalization. In B. Meltzer and D. Michie, editors, Machine Intelligence 5, pages 153–163. American Elsevier, 1970.Google Scholar
  23. PY97.
    C.H. Papadimitriou and M. Yannakakis. On the complexity of database queries. In Proceedings of the symposium on Principles of Database Systems, pages 12–19, Tucson, Arizona, 1997. ACM Press.Google Scholar
  24. Rou92.
    C. Rouveirol. Extensions of inversion of resolution applied to theory completion. In S. Muggleton, editor, Inductive Logic Programming. Academic Press, 1992.Google Scholar
  25. RS98.
    K. Rao and A. Sattar. Learning from entailment of logic programs with local variables. In Proceedings of the International Conference on Algorithmic Learning Theory. Springer-verlag, 1998. LNAI 1501.Google Scholar
  26. RT97.
    C. Reddy and P. Tadepalli. Learning Horn de_nitions with equivalence and membership queries. In International Workshop on Inductive Logic Programming, pages 243–255, Prague, Czech Republic, 1997. Springer. LNAI 1297.Google Scholar
  27. RT98.
    C. Reddy and P. Tadepalli. Learning first order acyclic Horn programs from entailment. In International Conference on Inductive Logic Programming, pages 23–37, Madison, WI, 1998. Springer. LNAI 1446.Google Scholar
  28. RTR96.
    C. Reddy, P. Tadepalli, and S. Roncagliolo. Theory guided empirical speedup learning of goal decomposition rules. In International Conference on Machine Learning, pages 409–416, Bari, Italy, 1996. Morgan Kaufmann.Google Scholar
  29. Sag88.
    Y. Sagiv. Optimizing datalog programs. In J. Minker, editor, Foundations of Deductive Databases and Logic Programming. Morgan Kaufmann, 1988.Google Scholar
  30. SB86.
    C. Sammut and R. Banerji. Learning concepts by asking questions. In R. Michalski, J. Carbonell, and T. Mitchell, editors, Machine Learning: An AI Approach, Volume II. Morgan Kaufman, 1986.Google Scholar
  31. Sha83.
    E.Y. Shapiro. Algorithmic Program Debugging. MIT Press, Cambridge, MA, 1983.Google Scholar
  32. Sha91.
    E. Shapiro. Inductive inference of theories from facts. In J. Lassez and G. Plotkin, editors, Computational Logic, pages 199–254. MIT Press, 1991.Google Scholar
  33. Val84.
    L.G. Valiant. A theory of the learnable. Communications of the ACM, 27(11):1134–1142, 1984.zbMATHCrossRefGoogle Scholar
  34. Val85.
    L.G. Valiant. Learning disjunctions of conjunctions. In Proceedings of the International Joint Conference of Artificial Intelligence, pages 560–566, Los Angeles, CA, 1985. Morgan Kaufmann.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Roni Khardon
    • 1
  1. 1.Division of InformaticsUniversity of EdinburghEdinburghScotland

Personalised recommendations