Inductive Logic Programming (ILP) [11] is a research
area in the intersection of machine learning and computational logic.
The main goal is development of a theory and algorithms for
inductive reasoning in first-order logic.
ILP aims to construct a theory covering given facts. Given a set of positive
examples , a set of negative examples , we construct a logic
program P such that and .
In case of noisy data we aim at a first-order logic formula that describes a
significant majority of positive examples and may be a non-significant part of
negative examples.