AI Seminar Series 2022: Amir Hossein

The AI Seminar is a weekly meeting at the University of Alberta where researchers interested in artificial intelligence (AI) can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics can be related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.

On March 18, Amir Hossein - a Ph. D. student at the Unversity of Alberta - presented "GPEX, A Framework For Interpreting Artificial Neural Networks" at the AI Seminar.

Machine learning researchers have long noted a trade-off between interpretability and prediction performance: traditional models are often understandable by humans but don’t achieve high prediction accuracy. Other models, however, can achieve impressive performance but are difficult for humans to interpret. In his seminar, Hossein presents a framework that reduces the gap between the two methods by training a Gaussian process (GP) to explain an artificial neural network(ANN) decisions. Their framework is implemented into a publicly-available tool called GPEX.

Watch the full presentation below:

Keep up-to-date on the AI Seminar Series by signing up for the mailing list.

Learn how Amii advances world-leading artificial intelligence and machine learning research: visit our Research page.