Abstract: We will present some recent research on the use of causality and counterfactual reasoning for providing explanations in data management and machine learning. Special emphasis will be placed on attribution scores such as causal responsibility and Shapley values, in particular Shap, for which we have provided efficient computation mechanisms.
Bio: Leopoldo Bertossi is an Emeritus Professor of the School of Computer Science, and a Faculty Member of the Multidisciplinary Institute for Data Science of Carleton University (Ottawa, Canada). He is also a Senior Researcher at the "Millennium Institute for Foundational Research on Data" (IMFD, Chile). His research interests are related to Data Management, Data Science and Artificial Intelligence, with focus on Explainable AI, Causality, Knowledge Representation, Computational Logic, Ontologies, Uncertainty Management.
