Dr. Sören Dittmer

Projects

1. Design-KIT: Artificial Intelligence in mechanical component development; TP: Deep Learning for geometry generation of mechanical components (01.10.2020 - 31.03.2022)
2. Magnetic Particle Imaging (since 01.03.2016)

Courses (Selection)complete list

1. Mathematical Methods in Machine Learning (Wintersemester 2023/2024)
2. Mathematical Foundations of AI (Sommersemester 2023)
3. Mathematical Foundations of Deep Learning (Wintersemester 2022/2023)
4. Mathematical Foundations of AI (Wintersemester 2022/2023)
5. Mathematical Foundations of AI (Sommersemester 2022)

Theses (Selection)complete list

1. Contrasting and motivating augmented contrastive learning (Jule Pätzold)
2. Inverse Problems Learning – data specific regularizations using projections (Julius Arkenberg)
3. Unsupervised Denoising von Magnetic-Particle-Imaging-Messungen durch Neuronale Netze (Nikolas Dreverhoff)
4. Differentiable architecture search - Fractional Kernel sizes in convolutional neural networks (Daniel Klosa)

Publications (Selection)complete list

1. M. Roberts, A. Hazan, S. Dittmer, J. H. F. Rudd, C. Schönlieb.
   The curious case of the test set AUROC.
   Zur Veröffentlichung eingereicht.
2. D. Erzmann, S. Dittmer.
   Equivariant Neural Operators for gradient-Consistent Topology Optimization .
   Zur Veröffentlichung eingereicht.
3. D. Erzmann, S. Dittmer, H. Harms, P. Maaß.
   DL4TO: A Deep Learning Library for Sample-Efficient Topology Optimization.
   Lecture Notes in Computer Science, Geometric Science of Information. GSI 2023 14071, Springer Verlag, 2023.

   DOI: 10.1007/978-3-031-38271-0_54

4. C. Arndt, A. Denker, S. Dittmer, J. Leuschner, J. Nickel, M. Schmidt.
   Model-based deep learning approaches to the Helsinki Tomography Challenge 2022.
   Applied Mathematics for Modern Challenges, 1(2), 2023.

   DOI: 10.3934/ammc.2023007

5. S. Dittmer, M. Roberts, J. Gilbey, A. Biguri, .. AIX-COVNET Collaboration, J. Preller, J. H. F. Rudd, J. A. D. Aston, C. Schönlieb.
   Navigating the development challenges in creating complex data systems.
   nature machine intelligence, 5:681-686, Springer Verlag, 2023.

   DOI: 10.1038/s42256-023-00665-x
   online at: https://www.nature.com/articles/s42256-023-00665-x#citeas