An Algorithm for Learning Abductive Rules

We propose an algorithm for learning abductive logic programs from examples. We consider the Abductive Concept Learning framework, an extension of the Inductive Logic Programming framework in which both the background and the target theories are abductive logic programs and the coverage of examples is replaced by abductive coverage. The two main bene ts of this integration are the increased expressive power of the background and target theories and the possibility of learning in presence of incomplete knowledge. We show that the algorithm is able to learn abductive rules and we present an application of the algorithm to a learning problem in which the background knowledge is incomplete.