Learnability of constrained logic programs

  • Sašo Džeroski
  • Stephen Muggleton
  • Stuart Russell
Position Papers Learnability

DOI: 10.1007/3-540-56602-3_148

Part of the Lecture Notes in Computer Science book series (LNCS, volume 667)
Cite this paper as:
Džeroski S., Muggleton S., Russell S. (1993) Learnability of constrained logic programs. In: Brazdil P.B. (eds) Machine Learning: ECML-93. ECML 1993. Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence), vol 667. Springer, Berlin, Heidelberg


The field of Inductive Logic Programming (ILP) is concerned with inducing logic programs from examples in the presence of back-ground knowledge. This paper defines the ILP problem and describes several syntactic restrictions that are often used in ILP. We then derive some positive results concerning the learnability of these restricted classes of logic programs, by reduction to a standard propositional learning problem. More specifically, k-literal predicate definitions consisting of constrained, function-free, nonrecursive program clauses are polynomially PAC-learnable under arbitrary distributions.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag 1993

Authors and Affiliations

  • Sašo Džeroski
    • 1
  • Stephen Muggleton
    • 2
  • Stuart Russell
    • 3
  1. 1.Institut Jožef StefanLjubljanaSlovenia
  2. 2.Oxford University Computing LaboratoryOxfordUK
  3. 3.Computer Science DivisionUniversity of CaliforniaBerkeleyUSA

Personalised recommendations