Combining Top-down and Bottom-up Techniques in Inductive Logic Programming

This paper describes a new methodfor inducing logic programs from examples which attempts to integrate the best aspects of existingILP methodsintoa singlecoherent framework. In particular, it combines a bottomup method similar to Golem with a topdown method similar to Foil. It also includes a method for predicate invention similar to Champ and an elegant solution to the noisy oracle" problem which allows the system to learn recursive programs without requiring a complete set of positive examples. Systematic experimental comparisons to both Golem and Foil on a range of problems are used to clearly demonstrate the advantages of the approach.

• Type: Conference
• Year: 1994
• Where: ICML
• Authors: John M. Zelle, Raymond J. Mooney, Joshua B. Konvisser
• Keywords: Bottomup Method, ICML 1994, Machine Learning, Methodsintoa Singlecoherent Framework, Topdown Method