CS Colloquium: Jerry Mendel (USC) - Explainable Ai (XAI) for Rule-Based Fuzzy Systems
Thu, Nov 11, 2021 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Jerry Mendel, Emeritus Professor of Electrical Engineering, University of Southern California
Talk Title: Explainable Ai (XAI) for Rule-Based Fuzzy Systems
Series: Computer Science Colloquium
Abstract: There is a sentiment in the fuzzy community that fuzzy rules would be of great value in XAI because such rules use words (which are modeled as fuzzy sets) and so they lend themselves naturally to XAI. This talk challenges that sentiment, in a constructive way. It explains why it is not valid to explain the output of Mamdani or TSK fuzzy systems using IF-THEN rules, but that it is valid to explain the output of such fuzzy systems as an association of the antecedents of a small subset of the original larger set of rules, using a phrase such as "These linguistic antecedents are symptomatic of this output". It also describes a novel multi-step approach to obtain such a small subset of rules for fuzzy systems, how Linguistic Approximation can be used to express the antecedent membership functions (the symptoms) linguistically, and a method for estimating the quality of linguistic explanations.
Register in advance for this webinar at:
After registering, attendees will receive a confirmation email containing information about joining the webinar.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Jerry Mendel received the Ph.D. degree in electrical engineering from the Polytechnic Institute of Brooklyn, Brooklyn, NY. Currently, he is (since Jan. 2018) Emeritus Professor of Electrical Engineering at the University of Southern California in Los Angeles. He has published close to 600 technical papers and is author and/or co-author of 12 books. He is a Life Fellow of the IEEE, a Distinguished Member of the IEEE Control Systems Society, and a Fellow of the International Fuzzy Systems Association. He was President of the IEEE Control Systems Society in 1986, a member of the Administrative Committee of the IEEE Computational Intelligence Society for nine years, and Chairman of its Fuzzy Systems Technical Committee and the Computing With Words Task Force of that Technical Committee. Among his awards are four IEEE Transactions best paper awards, a 1984 IEEE Centennial Medal, an IEEE Third Millenium Medal, and a Fuzzy Systems Pioneer Award from the IEEE Computational Intelligence Society. According to Google Scholar (as of Sept. 9, 2021) he has 58,428 citations, an h-index of 97 and an i10-index of 310. His present research interests include: type-2 fuzzy logic systems and XAI for rule-based systems.
Host: Mukund Raghothaman
Location: Online Zoom Webinar
WebCast Link: https://usc.zoom.us/webinar/register/WN_IgXrJer8SMOaS5VdwMdRFQ
Audiences: Everyone Is Invited
Contact: Computer Science Department