学术报告第202014期

报告题目：Interpretability in System Modeling: A Study in Granular Rule-Based Computing

报 告 人：Witold Pedrycz 教授（University of Alberta）

报告时间：2020年12月19日8：00

报告地点：线上报告

Abstract: The facets of interpretability and explainability have become more visible on the current agenda of system modeling and Artificial Intelligence. They are especially timely in light of the increasing complexity of systems one has to cope with. Interestingly, the investigations along this line have been intensively pursued in fuzzy rule-based models for some time.

In this presentation, we offer a systematic discussion on augmenting the interpretability of multivariable functional granular (fuzzy, in particular) rule-based models whose rules come in the generic form “if x is G_i then y =f_i(x,a_i)” where G_i is an information granule expressed in the input space and f_i serves as a local function from Rⁿ to R.

The interpretability mechanisms are focused on the elevation of interpretability of the conditions and conclusions of the rules. It is presented that augmenting interpretability of conditions is achieved by (i) decomposing a multivariable information granule into its one-dimensional components, (ii) their symbolic characterization, and (iii) linguistic approximation, which gives rise to the conditions in the form t(x_js is A), and t(essential x_js is A) where A is some reference information granule and t stands for a linguistic quantifier. We demonstrate that a formation of a granular conclusion B_i producing relational rules “if x is G_i then y is B_i” promotes an elevated interpretability level of the rules.

A hierarchy of interpretation mechanisms is systematically established. We also discuss how this increased interpretability associates with the reduced accuracy of the rules and how sound trade-offs between these features are formed.

Bio: Witold Pedrycz (IEEE Fellow, 1998) is Professor and Canada Research Chair (CRC) in Computational Intelligence 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. In 2009 Dr. Pedrycz was elected a foreign member of the Polish Academy of Sciences. In 2012 he was elected a Fellow of the Royal Society of Canada. In 2007 he received a prestigious Norbert Wiener award from the IEEE Systems, Man, and Cybernetics Society. He is a recipient of the 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, fuzzy modeling and Granular Computing, knowledge discovery and data science, pattern recognition, data science, knowledge-based neural networks, and control engineering. He has published papers in these areas. He is also an author of 21 research monographs and edited volumes covering various aspects of Computational Intelligence, data mining, and Software Engineering.

Dr. Pedrycz is vigorously involved in editorial activities. He is 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). He serves on an Advisory Board of IEEE Transactions on Fuzzy Systems and is a member of a number of editorial boards of international journals.