Abstract
This study evaluates the impact of concept descriptions on the behaviour and performance of concept formation processes (in which the data is either noisy or noise-free). Using a common architecture (ADECLU), different concept definitions are envisaged. These descriptions are of symbolic/numeric type, including statistical indices. The use of these indices introduces a "contrasting" between concept descriptions and reduces the effect of noise on predictive performance.
This work is supported by the Belgian National incentive-program for fundamental research in Artificial Intelligence. The scientific responsibility is assumed by the author.
Chapter PDF
References
Anderberg M.R. "Cluster analysis for applications", Academic Press, New York, 1973.
Decaestecker C. "Formation incrémentale de concepts par un critère d'adéquation". Proceedings of "4èmes Journées Française d'Apprentissage", 1989 (a).
Decaestecker C. "Incremental Concept Formation with Attribute Selection", Proceedings of the 4th EWSL (European Working Session on Learning), pp 49–58, 1989 (b).
Decaestecker C. "Description Contrasting in ADECLU: ADECLU/S", Technical Report IA-01-90, CADEPS (CAIRU), Université Libre de Bruxelles, Belgium, 1990.
Decaestecker C. Thesis, in preparation, Université Libre de Bruxelles, Belgium, 1991.
Fisher D.H. "Knowledge acquisition via incremental conceptual clustering", Machine Learning, 2, pp 139–172, 1987.
Fisher D.H. "Noise-Tolerant Conceptual Clustering", Proceedings of IJCAI-89, pp 825–830, 1989.
Gennari J.H., Langley P. and Fisher D. "Models of Incremental Concept Formation", Artificial Intelligence, vol. 40, No 1–3, 1989.
Gennari J.H. "Focused Concept Formation", Proceedings of the 6th International Workshop on Machine Learning, pp 379–382, 1989.
Goodman L.A. and Kruskal W.H. "Measures of association for cross classifications", J. of the American Stat. Assoc., vol. 49, pp 732–764, 1954.
Hanson S.J and Bauer M. "Machine Learning, Clustering and Polymorphy". In L.N. Kanal & J.F. Lemmer (Eds), Uncertainty in Artificial Intelligence, North-Holland, 1986.
Lebbe J., Vignes R., Darmoni S. "Les objets symboliques qualifiés, Application au diagnostic médical", Proceedings of the "2èmes Journées Symbolique-Numérique", Report no 487, LRI, Université Paris-Sud (Orsay), 1988.
Lebowitz M. "Experiments with incremental concept formation: UNIMEM", Machine Learning, 2, pp 103–138, 1987.
Michalski R.S. and Chilausky R.L. "Learning by being told and learning from examples ...", Policy analysis and Information Systems, vol.4, No 2, June 1980.
Quinlan J.R. "Induction of decision trees", Machine Learning, 1, pp 81–106, 1986.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Decaestecker, C. (1991). Description contrasting in incremental concept formation. In: Kodratoff, Y. (eds) Machine Learning — EWSL-91. EWSL 1991. Lecture Notes in Computer Science, vol 482. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0017016
Download citation
DOI: https://doi.org/10.1007/BFb0017016
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-53816-5
Online ISBN: 978-3-540-46308-5
eBook Packages: Springer Book Archive