Multidisciplinary Institute in Artificial intelligence

ABSTRACT

We will present recent research on the definition and computation of explanation scores, such as the Responsibility and Shap scores, concentrating mostly on the tractable computation of Shap explanation scores  on open-box classifiers defined by interesting classes of Boolean circuits. We will also present quite recent research on their computation on binary neural networks via knowledge compilation techniques.

LEOPOLDO BERTOSSI

Leopoldo Bertossi is a professor at the SKEMA Business School (Montreal, Canada). Since 2019, he is an Emeritus Professor with graduate supervisor status of the School of Computer Science, Carleton University (Ottawa, Canada); a Senior Researcher at the "Millennium Institute on Foundations of Data Research" (IMFD, Chile), and a Principal Investigator at the "National Basal Center for AI Research" (CENIA, Chile). Between 2019-22 he was affiliated with the "Universidad Adolfo Ibañez » (UAI, Chile) as a Full Professor at the Faculty of Engineering and Sciences, and the Director of the MSc and PhD Programs in Data Science. He is until now a Senior UAI Fellow. He has also been a Senior Computer Scientist at RelationalAI Inc., and a professor at the Pontifical Catholic University of Chile (PUC, Chile). He has PhD in Mathematics by the PUC, Chile. His broad research interests are related to Data Science and Artificial Intelligence; more specifically, he has done research on explainable AI, logical and uncertain knowledge representation and reasoning, data management, computational logic, ontological representations and reasoning, causality, and machine learning.