ECML 1993: Machine Learning: ECML-93 pp 56-64 | Cite as
Generalization under implication by using or-introduction
Abstract
In the area of inductive learning, generalization is a main operation. Already in the early 1970's Plotkin described algorithms for computation of least general generalizations of clauses under θ-subsumption. However, there is a type of generalizations, called roots of clauses, that is not possible to find by generalization under θ-subsumption. This incompleteness is important, since almost all inductive learners that use clausal representation perform generalization under θ-subsumption.
In this paper a technique to eliminate this incompleteness, by reducing generalization under implication to generalization under θ-subsumption, is presented. The technique is conceptually simple and is based on an inference rule from natural deduction, called or-introduction. The technique is proved to be sound and complete, but unfortunately it suffers from complexity problems.
References
- 1.M. Bain and S. Muggleton. Non-monotonic learning. Machine Intelligence, 12, 1991.Google Scholar
- 2.Jean H. Gallier. Logic for Computer Science: Foundations of Automatic Theorem Proving. John Wiley & Sons, 1987.Google Scholar
- 3.P. Idestam-Almquist. Generalization under implication by recursive antiunification. Submitted to the International Workshop on Inductive Logic Programming 1993.Google Scholar
- 4.P. Idestam-Almquist. Generalization under implication. Technical report, Department of Computer and Systems Sciences, Stockholm University, 1992. Report 92-020-SYSLAB.Google Scholar
- 5.P. Idestam-Almquist. Learning missing clauses by inverse resolution. In Proceedings of the International Conference on Fifth Generation Computer Systems 1992, Ohmsha, Tokyo, 1992.Google Scholar
- 6.Stéphane Lapointe and Stan Matwin. Sub-unification: A tool for efficient induction of recursive programs. In Proceedings of the Ninth International Conference on Machine Learning. Morgan Kaufmann, 1992.Google Scholar
- 7.J. W. Lloyd. Foundations of Logic Programming. Springer-Verlag, 1987. Second edition.Google Scholar
- 8.Stephen Muggleton. Inductive logic programming. New Generation Computing, 8(4):295–318, 1991.Google Scholar
- 9.Stephen Muggleton. Inverting implication. In Stephen Muggleton, editor, Proceedings of the International Workshop on Inductive Logic Programming, 1992.Google Scholar
- 10.Stephen Muggleton and Wray Buntine. Machine invention of first-order predicates by inverting resolution. In Proceedings of the Fifth International Conference on Machine Learning. Morgan Kaufmann, 1988.Google Scholar
- 11.Stephen Muggleton and C. Feng. Efficient induction of logic programs. In Proceedings of the First Conference on Algorithmic Learning Theory, Tokyo, 1990. Ohmsha Publishers.Google Scholar
- 12.Tim Niblett. A study of generalization in logic programs. In Proceedings of the Third European Working Session on Learning. Pitman, 1988.Google Scholar
- 13.Nilsson and Genesereth. Logic Foundations of Artificial Intelligence. Morgan Kaufmann, 1987.Google Scholar
- 14.G. D. Plotkin. Automatic Methods of Inductive Inference. PhD thesis, Edinburgh University, 1971.Google Scholar
- 15.J. Robinson. A machine-oriented logic based on the resolution principle. Journal of the ACM, 12(1), 1965.Google Scholar
- 16.Céline Rouveirol. Extensions of inversion of resolution applied to theory completion. In Stephen Muggleton, editor, Inductive Logic Programming. Academic Press, San Diego, CA, 1992.Google Scholar
- 17.Céline Rouveriol and Jean François Puget. Beyond inversion of resolution. In Proceedings of the Seventh International Conference on Machine Learning. Morgan Kaufmann, 1990.Google Scholar
- 18.Richmond H. Thomason. Symbolic Logic—An Introduction. McMillan Publishers, 1970.Google Scholar
- 19.Ruediger Wirth. Completing logic programs by inverse resolution. In Proceedings of the Fourth Working Session on Learning. Pitman, 1989.Google Scholar