Fuzzy Artificial Intelligence for Explainable Artificial Intelligence

Bernadette Bouchon-Meunier
Sorbonne Université, CNRS, LIP6, F-75005 Paris, France
Bernadette.Bouchon-Meunier@lip6.fr

Explainable Artificial Intelligence has been at the core of many developments in Artificial Intelligence in the recent years, following the DARPA incentives (https://www.darpa.mil/program/explainable-artificial-intelligence) to both produce more explainable artificial intelligence models while maintaining good learning performances, and enable the user to easily interact with intelligent systems. Several related concepts are inherent in the quality of intelligent systems, such as their understandability, their expressiveness or their interpretability. The latter has been in particular extensively investigated in the construction and analysis of fuzzy intelligent systems. We will review several of these aspects, mainly dealing with the capacity of an intelligent system to ex plain how it obtains results, and to provide the user with easily understandable outcomes, in light of the fuzzy paradigm. We will show that fuzzy models participate effectively in solutions to achieve one or the other of these goals, going beyond classic fuzzy rule-based systems.

Short biography of the speaker

Bernadette Bouchon-Meunier is a director of research emeritus at the National Centre for Scientific Research and Sorbonne University, the former head of the department of Databases and Machine Learning in the Computer Science Laboratory of the University Pierre et Marie Curie-Paris 6 (LIP6). She supervised 52 PhD students. She is the Editor-in-Chief of the International Journal of Uncertainty, Fuzziness and Knowledge-based Systems and the Co-executive director of the IPMU International Conference held every other year since 1986. B. Bouchon-Meunier is the (co)-editor of 32 books, and the (co)-author of five. She has (co)-authored more than 400 papers on approximate and similarity-based reasoning, as well as the application of fuzzy logic and machine learning techniques to decision-making, data mining, risk forecasting, information retrieval, user modelling, sensorial and emotional information processing.
She was elected President of the IEEE Computational Intelligence Society for 2020-2021. She is currently its Past President. She is an IEEE Life Fellow, an International Fuzzy Systems Association Fellow and an Honorary Member of the EUSFLAT Society. She received the 2012 IEEE Computational Intelligence Society Meritorious Service Award, the 2017 EUSFLAT Scientific Excellence Award, the 2018 IEEE CIS Fuzzy Systems Pioneer Award and the 2019 Outstanding Volunteer Award of the IEEE France Section.