论文信息 - Predicate Invention in ILP - an Overview

Predicate Invention in ILP - an Overview

Inductive Logic Programming (ILP) is a subfield of machine learning dealing with inductive inference in a first order Horn clause framework. A problem in ILP is how to extend the hypotheses language in the case that the vocabulary given initially is insufficient. One way to adapt the vocabulary is to introduce new predicates. In this paper, we give an overview of different approaches to predicate invention in ILP. We discuss theoretical results concerning the introduction of new predicates, and ILP-systems capable of inventing predicates. This work has been supported by the European Community ESPRIT project ILP (Inductive Logic Programming).

Irene Stahl | I. Stahl

[1] Masayuki Numao,et al. Efficient Learning of Logic Programs with Non-determinant, Non-discriminating Literals , 1991, ML.

[2] Masayuki Numao,et al. Discrimination-Based Constructive Induction of Logic Programs , 1992, AAAI.

[3] Rüdiger Wirth,et al. Learning by Failure to Prove , 1988, EWSL.

[4] S. C. Kleene,et al. Finite Axiomatizability of Theories in the Predicate Calculus Using Additional Predicate Symbols , 1952 .

[5] Rüdiger Wirth,et al. Constraints on Predicate Invention , 1991, ML.

[6] Michael J. Pazzani,et al. Relational Clichés: Constraining Induction During Relational Learning , 1991, ML.

[7] Pat Langley,et al. Improving Efficiency by Learning Intermediate Concepts , 1989, IJCAI.

[8] Céline Rouveirol,et al. Extensions of Inversion of Resolution Applied to Theory Completion , 1992 .

[9] Stephen Muggleton,et al. Machine Invention of First Order Predicates by Inverting Resolution , 1988, ML.

[10] H. Rice. Classes of recursively enumerable sets and their decision problems , 1953 .