Oberwolfach Reports

Full-Text PDF (1064 KB) | Introduction as PDF | Metadata | Table of Contents | OWR summary
Volume 15, Issue 1, 2018, pp. 559–589
DOI: 10.4171/OWR/2018/11

Published online: 2019-01-04

Mini-Workshop: Deep Learning and Inverse Problems

Simon R. Arridge[1], Maarten V. de Hoop[2], Peter Maaß[3] and Carola-Bibiane Schönlieb[4]

(1) University College London, UK
(2) Rice University, Houston, USA
(3) Universität Bremen, Germany
(4) University of Cambridge, UK

Machine learning and in particular deep learning offer several data-driven methods to amend the typical shortcomings of purely analytical approaches. The mathematical research on these combined models is presently exploding on the experimental side but still lacking on the theoretical point of view. This workshop addresses the challenge of developing a solid mathematical theory for analyzing deep neural networks for inverse problems.

No keywords available for this article.

Arridge Simon, de Hoop Maarten, Maaß Peter, Schönlieb Carola-Bibiane: Mini-Workshop: Deep Learning and Inverse Problems. Oberwolfach Rep. 15 (2018), 559-589. doi: 10.4171/OWR/2018/11