Position Papers Learnability

Machine Learning: ECML-93

Volume 667 of the series Lecture Notes in Computer Science pp 342-347

Date:

Learnability of constrained logic programs

  • Sašo DžeroskiAffiliated withInstitut Jožef Stefan
  • , Stephen MuggletonAffiliated withOxford University Computing Laboratory
  • , Stuart RussellAffiliated withComputer Science Division, University of California

* Final gross prices may vary according to local VAT.

Get Access

Abstract

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.