学术报告-Credibility, Explainability, and Interpretability in Machine Learning

题 目：Credibility, Explainability, and Interpretability in Machine Learning

主讲人：Witold Pedrycz

时 间：2023年11月30日（周四）上午9：00-10：30

地 点：腾讯会议 204-808-010 密码106106

现场直播：广东省知识产权大数据重点实验室 工业中心106

主讲人简介：

Witold Pedrycz (IEEE Life Fellow) is Professor in the Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada. He is also with the Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland. Dr. Pedrycz is a foreign member of the Polish Academy of Sciences and a Fellow of the Royal Society of Canada. He is a recipient of several awards including Norbert Wiener award from the IEEE Systems, Man, and Cybernetics Society, IEEE Canada Computer Engineering Medal, a Cajastur Prize for Soft Computing from the European Centre for Soft Computing, a Killam Prize, a Fuzzy Pioneer Award from the IEEE Computational Intelligence Society, and 2019 Meritorious Service Award from the IEEE Systems Man and Cybernetics Society. His main research directions involve Computational Intelligence, Granular Computing, and Machine Learning, among others.

Professor Pedrycz serves as an Editor-in-Chief of Information Sciences, Editor-in-Chief of WIREs Data Mining and Knowledge Discovery (Wiley), and Co-editor-in-Chief of Int. J. of Granular Computing (Springer) and J. of Data Information and Management (Springer).

Abstract：

In this lecture, we discuss how the agenda of Machine Learning (ML) can be effectively realized by exploring information granules and stressing an importance of the holistic perspective at credibility, interpretability and explainability of ML predictors and classifiers.

We show how a fundamental framework of Granular Computing helps enhance the existing approaches towards a systematic realization of credibility, transparency, explainability and interpretability. The design facets of credibility are systematically analyzed. To proceed with a detailed discussion, a concise information granules-oriented design of rule-based architectures is elaborated on. In the sequel, the ideas of counterfactual explanation are studied.

中国十大娱乐赌博城网址

广东省知识产权大数据重点实验室

     2023年11月27日