Machine learning of credible classifications
We present an approach to concept discovery in machine learning based on searching for maximally general credible classifications. To be credible, a classification must provide decisions for all or nearly all possible values of the condition attributes, and these decisions must be adequately supported by evidence. Our objective is to find a classification for a domain that meets predefined quality criteria. For example, a classification can be sought whose coverage of the domain exceeds a user-defined threshold and whose decisions are supported by sufficient input instances.
Unable to display preview. Download preview PDF.
- 1.B. Barber and H.J. Hamilton. Attribute selection strategies for attribute-oriented generalization. In Advances in Artificial Intelligence, 11th Biennial Conference of the Canadian Society for Computational Studies of Intelligenc, AI '96, pages 429–441. Springer, Toronto, 1996.Google Scholar
- 2.E. Bloedorn and R. Michalski. The AQ17-DCI system for data-driven constructive induction. In Proc. of Ninth Int'l. Symp. on Methodologies for Intelligent Systems, pages 108–117, Zakopane, Poland, June 1996.Google Scholar
- 3.Y.D. Cai, N. Cercone, and J. Han. Attribute-oriented induction in relational databases. In Knowledge Discovery in Databases, pages 213–228. AAAI/MIT Press, Cambridge, MA, 1991.Google Scholar
- 4.C.L. Carter and H.J. Hamilton. Efficient attribute-oriented algorithms for knowledge discovery from large databases. IEEE Trans. on Knowledge and Data Engineering. To appear.Google Scholar
- 5.H.J. Hamilton, R.J. Hilderman, and N. Cercone. Attribute-oriented induction using domain generalization graphs. In Proceedings of the Eighth IEEE International Conference on Tools with Artificial Intelligence (ICTAI'96), pages 246–253, Toulouse, France, November 1996.Google Scholar
- 6.R.J. Hilderman, H.J. Hamilton, R.J. Kowalchuk, and N. Cercone. Parallel knowledge discovery using domain generalization graphs. In J. Komorowski and J. Zytkow, editors, Proceedings of the 1st European Conference on the Principles of Data Mining and Knowledge Discovery, pages 25–35, Trondheim, Norway, June 1997.Google Scholar
- 7.I.F. Imam. An empirical study on the incompetence of attribute selection criteria. In Proc. of Ninth Int'l. Symp. on Methodologies for Intelligent Systems, pages 458–467, Zakopane, Poland, June 1996.Google Scholar
- 8.S.K. Murthy and S. Salzberg. Decision tree induction: How effective is the greedy heuristic? In Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining (KDD-96), pages 222–227, Portland, OR, 1996.Google Scholar
- 9.Z. Pawlak. Rough Sets. Theoretical Aspects of Reasoning About Data. Kluwer, 1991.Google Scholar
- 10.J. R. Quinlan. C4.5 Programs for Machine Learning. Morgan Kaufmann, 1993.Google Scholar
- 12.N. Shan, H.J. Hamilton, W. Ziarko, and N. Cercone. Discovering classification knowledge in databases using rough sets. In Proc. of the 2nd International Conference on Knowledge Discovery and Data Mining (KDD'96), pages 271–274, Portland, OR, 1996.Google Scholar
- 13.N. Shan, H.J. Hamilton, W. Ziarko, and N. Cercone. Discretization of continuous valued attributes in attribute-value systems. In Proc. of the Fourth Int'l. Workshop on Rough Sets, Fuzzy Sets, and Machine Discovery (RFSD'96), pages 74–81, Tokyo, Japan, 1996.Google Scholar