Explainable Artificial Intelligence: Interrogating the AI systems

Invited Talk - 7 November, 11:00-12:00, Julia House

Abstract

Explainable AI (XAI) refers to methods and techniques in the application of AI technology such that the results of the solution can be understood by human experts. In this talk we will first argue about the necessity of XAI in the current technologically dependent world, and then we will mainly focus on one of the trickiest-to-be-explained part of AI, namely Machine Learning (ML). We will define the notions of Transparent and Black Box Models, we will discuss what constitutes explainable or interpretable Machine Learning and will analyze the dimensions of interpretability, types of data and the ways the Black Box ML models can be opened up. We will discuss several methodologies and implementation including one developed with our own laboratory. Finally, we will start scratching on the dynamics of argumentation for explainability, including some discussion on using argumentation for explanations in ML, as well as some ongoing work on using natural language to draft explanations for a logical argumentation framework based on Gorgias. Finally, a few things about two projects AI4EU (H2020) and SoCoLa (ΕΛΛΙΔΕΚ), where this work is based on, will be presented.

Bio

Nick Bassiliades (http://tinyurl.com/bassiliades) received his MSc in Applied Artificial Intelligence from the Computing Science Department of Aberdeen University, in 1992, and his PhD degree in parallel knowledge base systems from the School of Informatics at the Aristotle University of Thessaloniki, Greece, in 1998, where he is currently a Full Professor. His research interests include knowledge-based and rule systems, multiagent systems, ontologies, linked data and the Semantic Web. He has published more than 200 papers at journals, conferences, and books, has coauthored 4 books and co-edited 10 volumes. His published research has received over 3500 citations (h-index 29), while 4 of his conference papers have received awards. He has been the Program Chair of RuleML-2008, RuleML-2011@IJCAI, RuleML-2015, WIMS-2014, SETN-2016, ICTERI-2017, EUMAS-2020 and a member of the Program Committee of more than 130. He has been involved in 37 R&D projects leading 12 of them. During 2017 he has been a visiting lecturer at the Department of Computer Science of the University of Cyprus. He has been the general secretary of the Board of the Greek Artificial Intelligence Society; he is a director of RuleML, Inc., and also a member of the Greek Computer Society, the IEEE, and the ACM.