Prof Cecilia Zanni-MerkINSA Rouen Normandie, France
On the need of an Explainable Artificial Intelligence
Artificial Intelligence (AI) applications are increasingly present in the professional and private worlds. This is due to the success of technologies such as machine learning (and, in particular, deep learning approaches) and automatic decision-making that allow the development of increasingly robust and autonomous AI applications. Most of these applications are based on the analysis of historical data with the goal of learning models based on the experience recorded in these data to make decisions or predictions.
However, automatic decision-making by the means of Artificial Intelligence now raises new challenges in terms of human understanding of processes resulting from learning, of explanations of the decisions that are made (crucial issue when ethical or legal considerations are involved) and, also, of human-machine communication.
To meet these needs, the field of Explainable Artificial Intelligence has recently developed.
Indeed, according to the literature, the notion of intelligence can be considered under four aspects: a) the ability to perceive rich, complex and subtle information, b) the ability to learn in a particular environment or context; c) the ability to abstract, to create new meanings and d) the ability to reason, for planning and decision-making
These four skills are implemented by what is now called the "Explainable Artificial Intelligence (or XAI)" with the goal of building explanatory models, to try and overcome shortcomings of pure statistical learning by providing justifications, understandable by a human, for decisions or predictions made.
During this talk we will explore this fascinating new research field.
Cecilia Zanni-Merk is a Full Professor in Computer Science at INSA Rouen Normandie, the National Institute of Applied Sciences of Normandy (Rouen, France). She is also the head of the MIND (multi-agents, interaction, decision) research group of the LITIS (Laboratory of Computer Science, Information Processing and Systems) lab. She holds an MSc in Computer Science from National University of La Plata (Argentina) in 1988, a PhD in Computer Science from Aix-Marseille University (France) in 2004 and she has got her Research Habilitation from Strasbourg University (France) in 2014. Professor Zanni-Merk is the French representative on the 5th Technical Commitee (TC5 - Information Technology Applications) of IFIP (International Federation of Information Processing) and the French scientific coordinator of Interreg project HALFBACK.
She is the co-author of more than 20 articles in top-ranked journal papers (including Computers in Industry, Knowledge-Based Systems, Engineering Applications of Artificial Intelligence, International Journal of Web Semantics, Applied Ontology) and of more than 50 papers in important international conferences.
Her main research interests are in Knowledge Engineering, and more particularly in conceptual representation and inference processes applied to problem solving (conceptualisation, ontologies and formal models, rule-based reasoning - crisp, fuzzy, probabilistic, spatio-temporal -, case-based reasoning, knowledge and experience capitalisation).
Back to Keynote Speakers