Dr. Osmar Zaïane (Canada CIFAR AI Chair, Fellow at Amii and University of Alberta Professor) will deliver a keynote speech at the 34th Canadian AI Conference, happening online from May 25 to 28 this year.

The presentation -- From an interpretable predictive model to a model agnostic explanation -- focuses on rule-based learning methods, particularly associative classifiers. Associative classifiers can determine patterns from data and perform classification based on the features that are most indicative of prediction. Osmar will present a new associative classifier approach that is more accurate and generates a smaller model, and that can also be used in an explainable-AI pipeline to explain inferences from other black box classifiers, irrespective of the predictive model used inside the black box.

Other keynote speakers at the conference include: Dr. Doina Precup, Core Academic Member of Mila, Associate Professor at McGill University and Research Team Lead at DeepMind Montreal; as well as Dr. Graham Taylor, Associate Professor and Canada Research Chair in Machine Learning at the University of Guelph and Canada CIFAR AI Chair at the Vector Institute.

The Canadian AI Conference is sponsored by the Canadian Artificial Intelligence Association (CAIAC) and invites papers that present original work in all areas of theoretical and applied AI. Colocated with the Computer and Robot Vision conferences. These events (AI·CRV 2021) will bring together hundreds of leaders in research, industry, and government, as well as Canada's most accomplished students. They showcase Canada's ingenuity, innovation and leadership in intelligent systems and advanced information and communications technology.