First-order jk-clausal theories are PAC-learnable

Luc De Raedt, Sašo Džeroski
1994 Artificial Intelligence  
We present positive PAC-learning results for the nonmonotonic inductive logic programming setting. In particular, we show that first order range-restricted clausal theories that consist of clauses with up to k literals of size at most j each are polynomialsample polynomial-time PAC-learnable with one-sided error from positive examples only. In our framework, concepts are clausal theories and examples are finite interpretations. We discuss the problems encountered when learning theories which
more » ... y have infinite non-trivial models and propose a way to avoid these problems using a representation change called flattening. Finally, we compare our results to PAC-learnability results for the normal inductive logic programming setting. * First version January 1994, second and revised version May 1994.
doi:10.1016/0004-3702(94)90112-0 fatcat:5lpp7hoixjbrdkgnsstjhs34ya