Dr. Alexander Denker

Ehemaliger Mitarbeiter der WG Industrial Mathematics, Research Training Group π³


Information: Email ends with @uni-bremen.de

Theses (Selection)complete list

1. Active learning for semantic segmentation in digital pathology (Jannik Wildner)
2. Adversarial Examples in Deep-Learning-Rekonstruktionen am Beispiel von Computer-Tomographie (Fabian Schönfeld)
3. Fehlererkennung und –segmentierung von Stahlcoils unter Verwendung des Contrastive Learnings (Dennis Hottendorff)

Publications (Selection)complete list

1. A. Denker.
   Invertible Neural Networks and Normalizing Flows for Image Reconstruction.
   Dissertationsschrift, Universität Bremen, 2024.

   DOI: 10.26092/elib/2921

2. A. Denker, Z. Kereta, I. Singh, T. Freudenberg, T. Kluth, B. Maass, S. Arridge.
   Data-driven approaches for electrical impedance tomography image segmentation from partial boundary data.
   Applied Mathematics for Modern Challenges, 2(2):119-139, 2024.

   DOI: 10.3934/ammc.2024005

3. P. Fernsel, Z. Kereta, A. Denker.
   Convergence Properties of Score-Based Models using Graduated Optimisation for Linear Inverse Problems.
   2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP), 22.09.-25.09.2024, London, UK.
   IEEE, pp. 1-6, 2024.

   DOI: 10.1109/MLSP58920.2024.10734770

4. F. Altenkrüger, A. Denker, P. Hagemann, P. Maaß, G. Steidl.
   PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization.
   Inverse Problems, 39(6), 2023.

   online at: https://iopscience.iop.org/article/10.1088/1361-6420/acce5e/meta

5. C. Arndt, A. Denker, S. Dittmer, N. Heilenkötter, M. Iske, T. Kluth, P. Maaß, J. Nickel.
   Invertible residual networks in the context of regularization theory for linear inverse problems.
   Inverse Problems, 39(12), IOPscience, 2023.

   DOI: 10.1088/1361-6420/ad0660
   online at: https://iopscience.iop.org/article/10.1088/1361-6420/ad0660

© Zentrum für Industriemathematik 2008-2023