Pac-Learning Nondeterminate Clauses
نویسنده
چکیده
Several practical inductive logic programming systems eeciently learn \determinate" clauses of constant depth. Recently it has been shown that while nonrecursive constant-depth determi-nate clauses are pac-learnable, most of the obvious syntactic generalizations of this language are not pac-learnable. In this paper we introduce a new restriction on logic programs called \locality", and present two formal results. First, the language of nonrecursive clauses of constant locality is pac-learnable. Second, the language of nonrecursive clauses of constant locality is strictly more expressive than the language of nonrecursive determi-nate clauses of constant depth. Hence, constant-locality clauses are a pac-learnable generalization of constant-depth determinate clauses.
منابع مشابه
Some Lower Bounds for the Computational Complexity of Inductive Logic Programming
The eld of Inductive Logic Programming (ILP), which is concerned with the induction of Horn clauses from examples and background knowledge , has received increased attention over the last time. Recently, some positive results concerning the learnability of restricted logic programs have been published. In this paper we review these restrictions and prove some lower-bounds of the computational c...
متن کاملPat-learning Nondeterminate Clauses
Several practical inductive logic programming systems efficiently learn “determinate” clauses of constant depth. Recently it has been shown that while nonrecursive constant-depth determinate clauses are pat-learnable, most of the obvious syntactic generalizations of this language are not pat-learnable. In this paper we introduce a new restriction on logic programs called “locality”, and present...
متن کاملPac-Learning Non-Recursive Prolog Clauses
Recently there has been an increasing amount of research on learning concepts expressed in subsets of Prolog; the term inductive logic programming (ILP) has been used to describe this growing body of research. This paper seeks to expand the theoretical foundations of ILP by investigating the pac-learnability of logic programs. We focus on programs consisting of a single function-free non-recurs...
متن کاملPac - learning Recursive Logic Programs : Negative
In a companion paper it was shown that the class of constant-depth determinate k-ary recursive clauses is eeciently learnable. In this paper we present negative results showing that any natural generalization of this class is hard to learn in Valiant's model of pac-learnability. In particular, we show that the following program classes are cryptographically hard to learn: programs with an unbou...
متن کاملLearning Logic Programs with Random Classification Noise
We consider the learnability of classes of logic programs in the presence of noise, assuming that the label of each example is reversed with a xed probability. We review the polynomial PAC learnability of nonrecursive, determinate, constant-depth Horn clauses in the presence of such noise. This result is extended to an analogous class of recursive logic programs that consist of a recursive clau...
متن کامل