Mini-Workshop: Deep Learning and Inverse Problems

  • Simon R. Arridge

    University College London, UK
  • Maarten V. de Hoop

    Rice University, Houston, USA
  • Peter Maaß

    Universität Bremen, Germany
  • Carola-Bibiane Schönlieb

    University of Cambridge, UK

Abstract

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.

Cite this article

Simon R. Arridge, Maarten V. de Hoop, Peter Maaß, Carola-Bibiane Schönlieb, Mini-Workshop: Deep Learning and Inverse Problems. Oberwolfach Rep. 15 (2018), no. 1, pp. 559–589

DOI 10.4171/OWR/2018/11