Also on zoom - https://umd.zoom.us/j/96718034173?pwd=clNJRks5SzNUcGVxYmxkcVJGNDB4dz09
Over the last decade, deep models have enjoyed wide empirical success. However, in practice, these models are not reliable due to their sensitivity against adversarial or natural input distributional shifts as well as a lack of meaningful reasoning behind their predictions. In this talk, I will show that a root cause of these issues is a heavy reliance of deep models on non-causal and spurious features in their inferences. I will then explain our progress in understanding failure modes of deep learning and outline a roadmap towards developing trustworthy learning paradigms.
Soheil Feizi is an assistant professor in the Computer Science Department at University of Maryland, College Park. Before joining UMD, he was a post-doctoral research scholar at Stanford University. He received his Ph.D. from Massachusetts Institute of Technology (MIT) in EECS with a minor degree in mathematics. He has received an NSF CAREER award in 2020 and is the recipient of several other awards including two best paper awards, a teaching award and multiple faculty awards from industry such as IBM, AWS and Qualcomm. He received the Ernst Guillemin award for his M.Sc. thesis, as well as the Jacobs Presidential Fellowship and the EECS Great Educators Fellowship at MIT.