Author:

Keywords:

inductive logic programming, computational learning theory, concept-learning, logic, clauses, Science & Technology, Technology, Computer Science, Artificial Intelligence, Computer Science, CLAUSES, 0801 Artificial Intelligence and Image Processing, 0802 Computation Theory and Mathematics, 1702 Cognitive Sciences, Artificial Intelligence & Image Processing, 4602 Artificial intelligence, 4603 Computer vision and multimedia computation, 4611 Machine learning

Abstract:

Three different formalizations of concept-learning in logic (as well as some variants) are analyzed and related. It is shown that learning from interpretations reduces to learning from entailment, which in rum reduces to learning from satisfiability. The implications of this result for inductive logic programming and computational learning theory are then discussed, and guidelines for choosing a problem-setting are formulated. (C) 1997 Elsevier Science B.V.