Browsing by Author "Schönlieb, Carola"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Deep Learning and Inverse Problems
    (Oberwolfach : Mathematisches Forschungsinstitut Oberwolfach gGmbH, 2019) Arridge, Simon; de Hoop, Maarten; Maass, Peter; Öktem, Ozan; Schönlieb, Carola; Unser, Michael
    Big data and deep learning are modern buzz words which presently infiltrate all fields of science and technology. These new concepts are impressive in terms of the stunning results they achieve for a large variety of applications. However, the theoretical justification for their success is still very limited. In this snapshot, we highlight some of the very recent mathematical results that are the beginnings of a solid theoretical foundation for the subject.
  • Thumbnail Image
    Item
    Mini-Workshop: Deep Learning and Inverse Problems
    (Zürich : EMS Publ. House, 2018) de Hoop, Maarten; Maaß, Peter; Schönlieb, Carola
    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.