Robustness in AI

by Nicolas Thome, Sorbonne University, France
Summary:
The recent success of AI and deep learning still faces important robustness issues. In this talk, I will discuss open problems and solutions for improving i) uncertainty quantification, ii) direct optimization of rank losses, and iii) limiting mistake severity.
Bio:
Nicolas Thome is a full professor at Sorbonne University (Paris). His research activities cover machine learning and deep learning for understanding low-level signals, such as vision, time series, and robotics. His current research interests include robustness in AI, multi-modal foundation models for autonomous agents, and physics-informed machine learning. He is involved in several French, European, and international collaborative research projects on artificial.
Find out more information related to our research at the LIVIA website: liviamtl.ca/