This paper demonstrates the capabilities of FOIDL, an inductive logic programming (ILP) system whose distinguishing characteristics are the ability to produce first-order decision lists, the use of an output completeness assumption to provide implicit negative examples, and the use of intensional background knowledge. The development of FOIDL was originally motivated by the problem of learning to generate the past tense of English verbs; however, this paper demonstrates its superior performance on two different sets of benchmark ILP problems. Tests on the finite element mesh design problem show that FOIDL's decision lists enable it to produce better results than all other ILP systems whose results on this problem have been reported. Tests with a selection of list-processing problems from Bratko's introductory Prolog text demonstrate t hat the combination of implicit negatives and intensionality allow FOIDL to learn correct programs from far fewer examples than FOIL.

PDF, PS

Technical Report, Artificial Intelligence Lab, University of Texas at Austin.

@techreport{califf:tech96, title={Advantages of Decision Lists and Implicit Negative in Inductive Logic Programming}, author={Mary Elaine Califf and Raymond J. Mooney}, month={January}, institution={Artificial Intelligence Lab, University of Texas at Austin}, url="http://www.cs.utexas.edu/users/ai-lab?califf:tech96", year={1996} }