Date & Time:
Tuesday, October 12, 2021; 1:00 PM EST
Deep learning is emerging as powerful tool to solve challenging inverse problems in computational imaging, including basic image restoration tasks like denoising and deblurring, as well as image reconstruction problems in medical imaging. This talk will give an overview of the state-of-the-art supervised learning techniques in this area and discuss two recent innovations: deep equilibrium architectures, which allows one to train an effectively infinite-depth reconstruction network; and model adaptation methods, that allow one to adapt a pre-trained reconstruction network to changes in the imaging forward model at test time.
Prof. Greg Ongie
Dr. Greg Ongie is an Assistant Professor in Mathematical and Statistical Sciences at Marquette University in Milwaukee, WI. Prior to this, he held postdoctoral positions at University of Chicago and University of Michigan. He received the PhD in Applied Mathematics from University of Iowa in 2016. His research interests include computational imaging, machine learning, and the mathematics of deep learning.