An active area of research in machine learning is learning logic programs from examples; this subarea is sometimes called inductive logic programming. This paper investigates this problem formally, using as our primary technical tool the method of prediction-preserving reducibilities and the model of polynomial predictability introduced by Pitt and Warmuth 1990]. We focus on the learnability of various generalizations of the language of constant-depth determinate clauses, which is used by several practical learning systems. We show that a single determinate clause of logarithmic depth is not polynomially predictable, under cryptographic assumptions. We then establish a close connection between the learnability of a single clause with k \free" variables and the learnability of DNF; a close connection is also shown between the learnability of a single clauses with bounded indeterminacy and the learnability of k-term DNF, leading to a prediction algorithm for a class of clauses with bounded indeterminacy. We then deene two new classes of logic programs that allow indeter-minacy, but are easily pac-learnable. Finally we present a series of results showing that allowing recursion makes some simple logic programming languages hard to learn against an arbitrary distribution: in particular, one-clause constant depth determinate programs with arbitrary recursion are hard to learn, as are multi-clause constant depth determinate programs with linear recursion.
[1]
Leslie G. Valiant,et al.
On the learnability of Boolean formulae
,
1987,
STOC.
[2]
Leonard Pitt,et al.
Reductions among prediction problems: on the difficulty of predicting automata
,
1988,
[1988] Proceedings. Structure in Complexity Theory Third Annual Conference.
[3]
Wray L. Buntine.
Generalized Subsumption and Its Applications to Induction and Redundancy
,
1986,
Artif. Intell..
[4]
M. Kearns,et al.
Crytographic limitations on learning Boolean formulae and finite automata
,
1989,
STOC '89.
[5]
David Page,et al.
Generalization with Taxonomic Information
,
1990,
AAAI.
[6]
J. Ross Quinlan,et al.
Determinate Literals in Inductive Logic Programming
,
1991,
IJCAI.
[7]
David Page,et al.
Learning Constrained Atoms
,
1991,
ML.
[8]
Saso Dzeroski,et al.
Background Knowledge and Declarative Bias in Inductive Concept Learning
,
1992,
AII.