Vegard Antun: On Stability of Deep Learning in Image Reconstruction
Vegard Antun (Department of Mathematics, University of Oslo) will give a talk on April 23rd at 14:15 in the Erling Sverdrups plass, Niels Henrik Abels hus, 8th floor.
Vegard Antun is a PhD candidate at the Department of Mathematics of the University of Oslo
Title: On Stability of Deep Learning in Image Reconstruction
Abstract: Deep learning has been proposed as a promising tool to increase performance for image reconstruction in medical imaging. In this talk we will introduce the image reconstruction problem, and show, with a lot of examples, how trained neural networks are completely unstable for image reconstruction. We will then present a theoretical result showing how deep learning will typically encourage this type of behavior for image reconstruction and inverse problems in general.
Download the flyer here