Colloquium: Deep Learning meets Shearlets: Explainable Hybrid Solvers for Inverse Problems in Imaging Science

3 February 2022

Colloquium by Prof. Gitta Kutyniok, Ludwig-Maximilians-Universität München

Thursday, 03 Februar 2022 14:00, Zoom Meeting

Abstract: Pure model-based approaches are today often insufficient for solving complex inverse problems in medical imaging. At the same time, methods based on artificial intelligence, in particular, deep neural networks, are extremely successful, often quickly leading to state-of- the-art algorithms. However, pure deep learning approaches often neglect known and valuable information from the modeling world and suffer from a lack of interpretability.

In this talk, we will develop a conceptual approach towards inverse problems in imaging sciences by combining the model-based method of sparse regularization by shearlets with the data-driven method of deep learning. Our solvers pay particular attention to the singularity structures of the data. Focusing then on the inverse problem of (limited-angle) computed tomography, we will show that our algorithms significantly outperform previous methodologies, including methods entirely based on deep learning. Finally, we will also touch upon the issue of how to interpret the results of such algorithms, and present a novel, state- of-the-art explainability method based on information theory.

The official announcement and abstract of the talk can be found here: https://syncandshare.desy.de/index.php/s/Z7jAYtbSefEmW5P

Please contact DASHH office for the Zoom access information, see link below.

Further information concerning the speakers and the lectures can also be found here: Data Science Colloquium Hamburg