Toward Robust Real-World Inference: A New Perspective on Explanation-Based Learning

  • Gerald DeJong
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4212)


Over the last twenty years AI has undergone a sea change. The once-dominant paradigm of logical inference over symbolic knowledge representations has largely been supplanted by statistical methods. The statistical paradigm affords a robustness in the real-world that has eluded symbolic logic. But statistics sacrifices much in expressiveness and inferential richness, which is achieved by first-order logic through the nonlinear interaction and combinatorial interplay among quantified component sentences. We present a new form of Explanation Based Learning in which inference results from two forms of evidence: analytic (support via sound derivation from first-order representations of an expert’s conceptualization of a domain) and empirical (corroboration derived from consistency with real-world observations). A simple algorithm provides a first illustration of the approach. Some important properties are proven including tractability and robustness with respect to the real world.


Inference Rule Inductive Logic Programming Domain Theory Proof Tree Theory Revision 
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.


  1. 1.
    Bay, S.D., Shapiro, D.G., Langley, P.: Revising engineering models: Combining computational discovery with knowledge. In: Thirteenth European Conference on Machine Learning, pp. 10–22 (2002)Google Scholar
  2. 2.
    Brunk, C., Pazzani, M.J.: A lexical based semantic bias for theory revision. In: ICML, pp. 81–89 (1995)Google Scholar
  3. 3.
    Clark, P., Matwin, S.: Using qualitative models to guide inductive learning. In: ICML, pp. 49–56 (1993)Google Scholar
  4. 4.
    Cohen, W.W.: Incremental abductive ebl. Machine Learning 15(1), 5–24 (1994)Google Scholar
  5. 5.
    Cussens, J.: Parameter estimation in stochastic logic programs. Machine Learning 44(3), 245–271 (2001)zbMATHCrossRefGoogle Scholar
  6. 6.
    DeJong, G., Mooney, R.: Explanation-based learning: An alternative view. Machine Learning 1(2), 145–176 (1986)Google Scholar
  7. 7.
    DeRaedt, L., Kersting, K.: Probabilistic logic learning. SIGKDD Explorations 5(1), 31–48 (2003)CrossRefGoogle Scholar
  8. 8.
    Epshteyn, A., Garzaran, M., DeJong, G., Padua, D., Ren, G., Li, X., Yotov, K., Pingali, K.: Analytic models and empirical search. In: The Eighteenth International Workshop on Languages and Compilers for Parallel Computing (2005)Google Scholar
  9. 9.
    Genesereth, M., Nilsson, N.: Logical Foundations of Artificial Intelligence. Kaufmann, Los Altos (1987)zbMATHGoogle Scholar
  10. 10.
    Greinter, R.: The complexity of theory revision. Artificial Intelligence 107(2), 175–217 (1999)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Haddawy, P.: Generating bayesian networks from probablity logic knowledge bases. In: UAI, pp. 262–269 (1994)Google Scholar
  12. 12.
    Landwehr, N., Kersting, K., De Raedt, L.: nfoil: Integrating naïve bayes and foil. In: AAAI, pp. 795–800 (2005)Google Scholar
  13. 13.
    Lavrac, N., Dzeroski, S.: Inductive Logic Programming: Techniques and Applications. Ellis Horwood, New York (1994)zbMATHGoogle Scholar
  14. 14.
    Mitchell, T., Keller, R., Kedar-Cabelli, S.: Explanation-based learning: A unifying view. Machine Learning 1(1), 47–80 (1986)Google Scholar
  15. 15.
    Mooney, R., Bennett, S.: A domain independent explanation-based generalizer. In: AAAI, pp. 551–555 (1986)Google Scholar
  16. 16.
    Morik, K., Brockhausen, P., Joachims, T.: Combining statistical learning with a knowledge-based approach - a case study in intensive care monitoring. In: ICML, pp. 268–277 (1999)Google Scholar
  17. 17.
    Muggleton, S., De Raedt, L.: Inductive logic programming: Theory and methods. J. Log. Program. 19/20, 629–679 (1994)CrossRefGoogle Scholar
  18. 18.
    Nedellec, C., Rouveirol, C., Ade, H., Bergadano, F., Tausend, B.: Declarative bias in ILP. In: De Raedt, L. (ed.) Advances in Inductive Logic Programming, pp. 82–103. IOS Press, Amsterdam (1996)Google Scholar
  19. 19.
    Ourston, D., Mooney, R.: Theory refinement combining analytical and empirical methods. Artif. Intell. 66(2), 273–309 (1994)zbMATHCrossRefMathSciNetGoogle Scholar
  20. 20.
    Plaisted, D., Zhu, Y.: The Efficiency of Theorem Proving Strategies. Vieweg & Sohn, Wiesbaden (1999)Google Scholar
  21. 21.
    De Raedt, L., Dietterich, T., Getoor, L., Muggleton, S.H. (eds.): Probabilistic, Logical and Relational Learning. In: Dagstuhl Seminar Proceedings (2005)Google Scholar
  22. 22.
    De Raedt, L., Kramer, S. (eds.): Workshop on Attribute-Value and Relational Learning: Crossing the Boundaries at ICML 2000 (2000)Google Scholar
  23. 23.
    Roth, D.: On the hardness of approximate reasoning. In: IJCAI, pp. 613–619 (1993)Google Scholar
  24. 24.
    Russell, S.J., Grosof, B.N.: A declarative approach to bias in concept learning. In: Proc. of AAAI 1987, Seattle, WA, pp. 505–510 (1987)Google Scholar
  25. 25.
    Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 2nd edn. Prentice-Hall, Englewood Cliffs (2003)Google Scholar
  26. 26.
    Saitta, L., Botta, M., Neri, F.: Multistrategy learning and theory revision. Machine Learning 11(2-3), 153–172 (1993)CrossRefGoogle Scholar
  27. 27.
    Towell, G.G., Shavlik, J.W.: Knowledge-based artificial neural networks. Artif. Intell. 70(1-2), 119–165 (1994)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Gerald DeJong
    • 1
  1. 1.Computer Science DepartmentUniversity of Illinois at Urbana 

Personalised recommendations