AI Seminar Series 2021: Dr. Suchi Saria - Safe and Reliable AI

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 April 16, Dr. Suchi Saria presented "Safe and Reliable AI: Overview and Novel Approach Approaches for Learning and Monitoring."

As the use of machine learning in safety-critical domains becomes widespread, it's more important than ever to proactively address sources of failure and evaluate model reliability. However, achieving this can be difficult as ML models are vulnerable to being overly dependent on context (i.e., artifacts specific to the training dataset) on which the model was trained. In this talk, Dr. Saria looks at work in this area over the last five years and describes approaches for tackling challenges in building safe and reliable AI.

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.