Abstract
A central operation in an incremental learning system is the specialization of an incorrect theory in order exclude incorrect inferences. In this paper, we discuss what properties are to be required from such theory revision operations. In particular, we examine what it should mean for a revision to be minimal. As a surprising result, the seemingly most natural criterion, requiring revisions to produce maximally general correct specializations, leads to a number of serious problems. We therefore propose an alternative interpretation of minimality based on the notion of base revision from theory contraction work, and formally define it as a set of base revision postulates. We then present a revision operator (Mbr) that meets these postulates, and shown that it produces the maximally general correct revision satisfying the postulates, i.e., the revisions produced by Mbr are indeed minimal in our sense. The operator is implemented and used in Krt, the knowledge revision tool of the Mobal system.
Chapter PDF
Similar content being viewed by others
References
C. E. Alchourrón, P. Gärdenfors, and D. Makinson. On the logic of theory change: Partial meet contraction and revision functions. The Journal of Symbolic Logic, 50:510–530, 1985.
C. E. Alchourrón and D. Makinson. On the logic of theory change: contraction functions and their associated revision functions. Theoria, 48:14–37, 1982.
Luc DeRaedt. Interactive Concept-Learning. PhD thesis, Kath. Univ. Leuven, Leuven, Belgium, February 1991.
Werner Emde, Christopher U. Habel, and Claus-Rainer Rollinger. The discovery of the equator or concept driven learning. In IJCAI-83, pages 455–458, San Mateo, CA, 1983. Morgan Kaufman.
Werner Emde. An inference engine for representing multiple theories. In Katharina Morik, editor, Knowledge Representation and Organization in Machine Learning, pages 148–176. Springer Verlag, Berlin, New York, 1989.
Peter Gärdenfors. Knowledge in Flux — Modeling the Dynamics of Epistemic States. MIT Press, Cambridge, MA, 1988.
Charles Ling. Non-monotonic specialization. In Proc. Inductive Logic Programming Workshop, Portugal, 1991.
Stephen Muggleton and Michael Bain. Non-monotonic learning. In Stephen Muggleton, editor, Inductive Logic Programming. Academic Press, London, New York, 1992.
Elliot Mendelson. Introduction to Mathematical Logic. Wadsworth & Brooks, Belmont, CA, third edition, 1987.
K. Morik, S. Wrobel, J.U. Kietz, and Werner Emde. Knowledge Acquisition and Machine Learning: Theory, Methods, and Applications. Academic Press, London, New York, in press. To appear.
Bernhard Nebel. Reasoning and Revision in Hybrid Representation Systems. Springer Verlag, Berlin, New York, 1989. Doctoral Dissertation.
Gordon D. Plotkin. A note on inductive generalization. In B. Meltzer and D. Michie, editors, Machine Intelligence 5, chapter 8, pages 153–163. Edinburgh Univ. Press, Edinburgh, 1970.
Claude Sammut and Ranan B. Banerji. Learning concepts by asking questions. In R.S. Michalski, J.G. Carbonell, and T.M. Mitchell, editors, Machine Learning — An Artificial Intelligence Approach, volume II, chapter 7, pages 167–191. Morgan Kaufman, San Mateo, CA, 1986.
Ehud Y. Shapiro. Algorithmic Program Debugging. ACM Distinguished Doctoral Dissertations. The MIT Press, Cambridge, Mass., 1983.
E. Sommer, K. Morik, J-M. André, and M. Uszynski. What online machine learning can do for knowledge acquisition — a case study. To appear, 1993.
Stefan Wrobel. Automatic representation adjustment in an observational discovery system. In D. Sleeman, editor, Proc. of the 3rd Europ. Working Session on Learning, pages 253–262, London, 1988. Pitman.
Stefan Wrobel. Demand-driven concept formation. In Katharina Morik, editor, Knowledge Representation and Organization in Machine Learning, pages 289–319. Springer Verlag, Berlin, New York, 1989.
Stefan Wrobel. Representation adjustment by demand-driven concept formation. in preparation, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wrobel, S. (1993). On the proper definition of minimality in specialization and theory revision. In: Brazdil, P.B. (eds) Machine Learning: ECML-93. ECML 1993. Lecture Notes in Computer Science, vol 667. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56602-3_128
Download citation
DOI: https://doi.org/10.1007/3-540-56602-3_128
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56602-1
Online ISBN: 978-3-540-47597-2
eBook Packages: Springer Book Archive