Embedded Files
"Trustworthy Explanations in Data Science for Societal Challenges"
by Jerzy Stefanowski
This lecture concerns issues of using artificial intelligence and data science in social good and involving humans in the evaluation of such intelligent systems, particularly with the use of explainable artificial intelligence (XAI) methods. Trustworthy explanations are important for mining societal data and applying machine learning there because they build public trust, ensure fairness and help decision makers to act safely. Among the many societal challenges, we will discuss two case studies of analyzing urban infrastructure for older adults and people with disabilities. We will demonstrate how data science methods can be used to assess the city’s compliance with the “15-minute city” concept and to determine the placement of benches and “rest stops” for these individuals. Next, we will discuss in more detail the challenges of evaluating selected XAI methods, as well as the difficulties involved in conducting evaluation studies involving human participants. One of presented cases will also concern fairness issues while others demonstrate challenges for using counterfactual explanations.
The final result is a functional, accessible restoration tool with a simple interface, capable of handling both individual and batch processing. This work demonstrates the practical and emotional value of AI in post-disaster recovery, offering a way to restore not only images, but memory itself.
Short Bio
Jerzy Stefanowski works as a full professor at Poznan University of Technology, Institute of Computing Science. He received his Ph.D, and Habilitation degrees from the same University. In 2021 he was elected as a member of Polish Academy of Science, where he also plays a role of a Chair of Scientific Council of Institute of Computer Science (IPI PAN) in Warsaw and vice-president of Thematic Committee of PAN on Computer Science. Since 2022 he is leading the Machine Learning Lab at Poznan University of Technology. His research interests include data mining, machine learning and intelligent decision support. Major results are concerned with: ensemble classifiers, learning from class-imbalanced data, online learning from evolving data streams, explainable AI, induction of various types of rules, data preprocessing, generalizations of rough set theory, descriptive clustering of texts and medical applications of data mining. He is the author and co-author of over 170 research papers and 2 books, which are highly cited. He was a visiting professor or researcher in several universities, mainly in France, Italy, Belgium, Spain and Germany
In addition to his research activities he served in a number of organizational roles such as vice-president of Polish Artificial Intelligence Society (2014-2026); co-founder and co-leader of Polish Special Interest Group on Machine Learning. Moreover, he is the Editor in Chief of Foundations of Computing and Decision Science journal since 2012.
Google Sites
Report abuse