报 告 人：Professor Thierry Denoeux, Université de Technologie de Compiègne (UTC), France
邀 请 人：岳晓冬 副教授
The Dempster-Shafer theory of belief functions is a formal framework for modeling and reasoning with uncertainty. Many supervised and unsupervised learning algorithms based on belief functions have been proposed in recent years. Several new developments will be reviewed. The notion of evidential clustering, based on belief functions, will be shown to encompass most clustering notions (including, fuzzy, possibilistic and rough clustering), which makes it possible to evaluate and combine partitions produced by different kinds of clustering algorithms. Another development concerns learning from uncertain data. Applications include learning from fuzzy data, and partially supervised learning, in which class labels are uncertain. The evidential EM (E2M) algorithm will be introduced and several real applications will be presented.
Thierry Denoeux is a Full Professor (Exceptional Class) with the Department of Information Processing Engineering at the Université de Technologie de Compiègne (UTC), France. His research interests concern the management of uncertainty in intelligent systems. His main contributions are in the theory of belief functions with applications to pattern recognition, data mining and information fusion. He has published more than 200 journal and conference papers in this area. He is the Editor-in-Chief of the International Journal of Approximate Reasoning, and an Associate Editor of several journals including Fuzzy Sets and Systems and the International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems (IJUFKS).