English

Pac-Learning Recursive Logic Programs: Efficient Algorithms

Artificial Intelligence 2014-11-17 v1

Abstract

We present algorithms that learn certain classes of function-free recursive logic programs in polynomial time from equivalence queries. In particular, we show that a single k-ary recursive constant-depth determinate clause is learnable. Two-clause programs consisting of one learnable recursive clause and one constant-depth determinate non-recursive clause are also learnable, if an additional ``basecase'' oracle is assumed. These results immediately imply the pac-learnability of these classes. Although these classes of learnable recursive programs are very constrained, it is shown in a companion paper that they are maximally general, in that generalizing either class in any natural way leads to a computationally difficult learning problem. Thus, taken together with its companion paper, this paper establishes a boundary of efficient learnability for recursive logic programs.

Keywords

Cite

@article{arxiv.cs/9505104,
  title  = {Pac-Learning Recursive Logic Programs: Efficient Algorithms},
  author = {W. W. Cohen},
  journal= {arXiv preprint arXiv:cs/9505104},
  year   = {2014}
}

Comments

See http://www.jair.org/ for any accompanying files