On Learning and Logic

  • György Turán
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4005)


A brief survey is given of learning theory in a logic framework, concluding with some topics for further research. The idea of learning using logic is traced back to Turing’s 1951 radio address [15]. An early seminal result is that clauses have a least general generalization [18]. Another important concept is inverse resolution [16]. As the most common formalism is logic programs, the area is often referred to as inductive logic programming, with yearly ILP conferences since 1991.


Logic Program Rational Revision Belief Revision Query Complexity Inductive Logic Programming 
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.
    Alchourrón, C.E., Gärdenfors, P., Makinson, D.: On the logic of theory change: partial meet functions for contraction and revision. J. Symbolic Logic 50, 510–530 (1985)CrossRefMathSciNetMATHGoogle Scholar
  2. 2.
    Arias, M., Khardon, R., Maloberti, J.: Learning Horn expressions with LogAn-H, Tufts University Computer Science Technical Report 2005-4Google Scholar
  3. 3.
    Cohen, W.W., Page, C.D.: Polynomial learnability and inductive logic programming: methods and results. New Generation Computing 13, 369–409 (1995)CrossRefGoogle Scholar
  4. 4.
    Frazier, M., Pitt, L.: CLASSIC learning. Machine Learning 25, 151–193 (1996)CrossRefMATHGoogle Scholar
  5. 5.
    Getoor, L., Friedman, N., Koller, D., Pfeffer, A.: Learning probabilistic relational models. In: Džeroski, S., Lavrač, N. (eds.) Relational Data Mining, pp. 307–335. Kluwer, Dordrecht (2001)Google Scholar
  6. 6.
    Goldsmith, J., Sloan, R.H., Szörényi, B., Turán, G.: Theory revision with queries: Horn, read-once and parity formulas. Artificial Intelligence 156, 139–176 (2004)CrossRefMathSciNetMATHGoogle Scholar
  7. 7.
    Grohe, M., Turán, G.: Learnability and definability in trees and similar structures. Theory of Computing Systems 37, 193–220 (2004)CrossRefMathSciNetMATHGoogle Scholar
  8. 8.
    Hegedűs, T.: Generalized teaching dimensions and the query complexity of learning. In: 8th Annual Conference on Computational Learning Theory, pp. 108–117 (1995)Google Scholar
  9. 9.
    Hellerstein, L., Pillaipakkamnatt, K., Raghavan, V., Wilkins, D.: How many queries are needed? J. of the ACM 43, 840–862 (1996)CrossRefMathSciNetMATHGoogle Scholar
  10. 10.
    Horváth, T., Turán, G.: Learning logic programs with structured background knowledge. Artificial Intelligence 128, 31–97 (2001)CrossRefMathSciNetMATHGoogle Scholar
  11. 11.
    Kelly, K.T., Schulte, O., Hendricks, V.: Reliable belief revision. In: Dalla Chiara, M.L., et al. (eds.) Logic and Scientific Methods. Kluwer, Dordrecht (1997)Google Scholar
  12. 12.
    Khardon, R.: Learning function-free Horn expressions. Machine Learning 37, 241–275 (1999)CrossRefMATHGoogle Scholar
  13. 13.
    Khardon, R., Roth, D.: Learning to reason. J. of the ACM 44, 697–725 (1997)CrossRefMathSciNetMATHGoogle Scholar
  14. 14.
    Martin, E., Osherson, D.: Scientific discovery based on belief revision. J. of Symbolic Logic 62, 1352–1370 (1997)CrossRefMathSciNetMATHGoogle Scholar
  15. 15.
    Muggleton, S.: Logic and learning: Turing’s legacy. In: Furukawa, K., Michie, D., Muggleton, S. (eds.) Machine Intelligence, vol. 13, pp. 37–56 (1994)Google Scholar
  16. 16.
    Muggleton, S., Buntine, W.: Machine invention of first-order predicates by inverting resolution. In: 5. International Machine Learning Conference, pp. 339–352 (1988)Google Scholar
  17. 17.
    Pagnucco, M., Rajaratnam, D.: Inverse resolution as belief change. In: 19. International Joint Conference on Artificial Intelligence, pp. 540–545 (2005)Google Scholar
  18. 18.
    Plotkin, G.D.: A note on inductive generalization. In: Meltzer, B., Michie, D. (eds.) Machine Intelligence, vol. 5, pp. 153–163 (1970)Google Scholar
  19. 19.
    Richardson, M., Domingos, P.: Markov logic networks. Machine Learning 62, 107–136 (2006)CrossRefGoogle Scholar
  20. 20.
    Wrobel, S.: Concept Formation and Knowledge Revision. Kluwer, Dordrecht (1994)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • György Turán
    • 1
    • 2
  1. 1.University of Illinois at ChicagoChicagoUSA
  2. 2.Research Group on Artificial IntelligenceHungarian Academy of Sciences and University of SzegedSzegedHungary

Personalised recommendations