Using logic rules for concept refinement learning in first order logic

Abstract

In this paper, it has been explored that the use of logic rules as key element in concept refinement Learning. A logic rule is a formal grammar in logic for expressing formation rules of a formal language. First order logic in Inductive Logic Programming(ILP) and programming language in Genetic Programming(GP) are formal languages, the logic rule is available to express syntax and semantics of them. Concept refinement learning including inductive concept learning by employing ILP and evolutionary concept learning by employing GP.A framework is presented that combining ILP and GP using logic rules for concept refinement learning in first order logic. The viability of our approach is illustrated by comparing the performance of our learner with that of other concept learners such as Progol, CfgGP, GGP on a variety of target concepts. We conclude with some observations about the merits of our approach and about possible extensions.