LCSR Seminar: Pablo Arbelaez “Towards Robust Artificial Intelligence”
I will discuss recent efforts at CinfonIA in enhancing interpretability in deep neural networks through the use of adversarial robustness and multimodal information.
Pablo Arbeláez received the PhD with honors in Applied Mathematics from the Université Paris Dauphine in 2005. He was Senior Research Scientist with the Computer Vision Group at UC Berkeley from 2007 to 2014. He currently holds a faculty position in the Department of Biomedical Engineering at Universidad de los Andes in Colombia. Since 2020, he leads the Center for Research and Formation in Artificial Intelligence (CinfonIA) at UniAndes. His research interests are in computer vision and machine learning, in which he has worked on several problems, including perceptual grouping, object recognition and the analysis of biomedical images.