Incremental learning of logic programs

  • M. R. K. Krishna Rao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 997)


In this paper, we identify a class of polynomial-time learnable logic programs. These programs can be learned from examples in an incremental fashion using the already defined predicates as background knowledge. Our class properly contains the class of innermost simple programs of [20] and the class of hereditary programs of [12,13]. Standard programs for multiplication, quick-sort, reverse and merge are a few examples of programs that can be handled by our results but not by the earlier results of [12, 13, 20].


Background Knowledge Logic Program Logic Programming Predicate Symbol 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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    G. Aguzzi and U. Modigliani (1993), Proving termination of logic programs by transforming them into equivalent term rewriting systems, Proc. of FST&TCS'93, LNCS 761, pp. 114–124.Google Scholar
  2. 2.
    S. Arikawa, S. Miyano, A. Shinohara, T. Shinohara and A. Yamamoto (1992), Algorithmic learning theory and elementary formal systems, IEICE Trans. Inf. & Sys. E75-D, pp. 405–414.Google Scholar
  3. 3.
    A. Blumer, A. Ehrenfeucht, D. Haussler and M.K. Warmuth (1989), Learnability and Vapnik-Chervonenkis dimension, JACM 36, pp. 929–965.Google Scholar
  4. 4.
    P.G. Bosco, E. Giovannetti and C. Moiso (1988), Narrowing vs. SLD-resolution, Theoretical Computer Science 59, pp. 3–23.CrossRefGoogle Scholar
  5. 5.
    S. Dzeroski, S. Muggleton and S. Russel (1992), PAC-learnability of determinate logic programs, Proc. of COLT'92, pp. 128–135.Google Scholar
  6. 6.
    M. Hanus (1994), The integration of functions into logic programming: a survey, J. Logic Prog. 19/20, pp. 583–628.Google Scholar
  7. 7.
    J.-M. Hullot (1980), Canonical forms and unification, Proc. of CADE'80, LNCS 87, pp. 318–334.Google Scholar
  8. 8.
    K. Ito and A. Yamamoto (1992), Polynomial-time MAT learning of multilinear logic programs, Proc. of ALT'92, LNAI 743, pp. 63–74.Google Scholar
  9. 9.
    M.R.K. Krishna Rao, D. Kapur and R.K. Shyamasundar (1991), A Transformational methodology for proving termination of logic programs, Proc. of CSL'91, LNCS 626, pp. 213–226.Google Scholar
  10. 10.
    M.R.K. Krishna Rao, D. Kapur and R.K. Shyamasundar (1993), Proving termination of GHC programs, Proc. of ICLP'93, pp. 720–736.Google Scholar
  11. 11.
    J. W. Lloyd (1987), Foundations of Logic Programming, Springer-Verlag.Google Scholar
  12. 12.
    S. Miyano, A. Shinohara and T. Shinohara (1991), Which classes of elementary formal systems are polynomial-time learnable?, Proc. of ALT'91, pp. 139–150.Google Scholar
  13. 13.
    S. Miyano, A. Shinohara and T. Shinohara (1993), Learning elementary formal systems and an application to discovering motifs in proteins, Tech. Rep. RIFIS-TR-CS-37, RIFIS, Kyushu University.Google Scholar
  14. 14.
    S. Muggleton and L. De Raedt (1994), Inductive logic programming: theory and methods, J. Logic Prog. 19/20, pp. 629–679.CrossRefGoogle Scholar
  15. 15.
    B.K. Natarajan (1991), Machine Learning: A Theoretical Approach, Morgan-Kaufmann.Google Scholar
  16. 16.
    Y. Sakakibara (1990), Inductive inference of logic programs based on algebraic semantics, New Gen. Comp. 7, pp. 365–380.Google Scholar
  17. 17.
    E. Shapiro (1981), Inductive inference of theories from facts, Tech. Rep., Yale Univ.Google Scholar
  18. 18.
    E. Shapiro (1983), Algorithmic Program Debugging, MIT Press.Google Scholar
  19. 19.
    R.K. Shyamasundar, M.R.K. Krishna Rao and D. Kapur (1992), Rewriting concepts in the study of termination of logic Programs, Proc. of ALPUK'92 conf. (edited by K. Broda), Workshops in Computing series, pp. 3–20, Springer-Verlag.Google Scholar
  20. 20.
    A. Yamamoto (1993), Generalized unification as background knowledge in learning logic programs, Proc. of ALT'93, LNAI 744, pp. 111–122. Revised version appears as Learning logic programs using definite equality theories as background knowledge, IEICE Trans. Inf. & Syst. E78-D, May 1995, pp. 539–544.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • M. R. K. Krishna Rao
    • 1
    • 2
  1. 1.Computer Science GroupTata Institute of Fundamental ResearchColaba, BombayIndia
  2. 2.Max-Planck-Institut für Informatik Im StadtwaldSaarbrückenGermany

Personalised recommendations