Dr. Maximilian Schmidt
Research Assistant WG Industrial Mathematics, Research Training Group π3Email: maximilian.schmidt@uni-bremen.de
Phone: (0421) 218-63826
ORCID iD: 0000-0001-8710-1389
CV
Theses
- Master Thesis (12/2018)
-
Investigation of Neural Capsule Networks in the Context of Image Classification and Semantic Segmentation
German title: Untersuchung Neuronaler Kapsel-Netze im Kontext der Bildklassifikation und Semantischen Segmentierung
Supervisors: Prof. Dr. Dr. h.c. Peter Maaß, Dr. Jens Behrmann
University of Bremen - Bachelor Thesis (09/2016)
-
Classification on MALDI Data with Non-Negative Matrix Factorization and Supervised Learning
German title: Klassifikation auf MALDI-Daten mit nichtnegativer Matrixfaktorisierung und überwachtem Lernen
Supervisors: Prof. Dr. Dr. h.c. Peter Maaß, Delf Lachmund
University of Bremen
Work & Research
- PhD Student RTG π3 (since 09/2019)
-
R3-10: Learning Tikhonov Functionals for Inverse Problems
Center for Industrial Mathematics
University of Bremen - Research Assistant (since 01/2019)
-
Deep Learning & Inverse Problems
Center for Industrial Mathematics
University of Bremen - Internship (08/2017 - 10/2017)
-
Size Reduction of Artificial Neural Networks
Bosch, Research Department
Hildesheim, Germany - Student Assistant (08/2014 - 12/2018)
-
Machine Learning & MALDI Imaging
Center for Industrial Mathematics
University of Bremen
Research Areas
- Deep Learning
- Inverse Problems
- Computed Tomography
Projects
- Neural networks in MALDI imaging (since 01.10.2016)
Courses (Selection)
- Computerpraktikum (Wintersemester 2019/2020)
- Übungen Mathematical Foundations of Machine Learning (Sommersemester 2019)
Theses (Selection)
- Active learning for semantic segmentation in digital pathology (Jannik Wildner)
- Out of Distribution Detection for Purity Assessment of Pellets using Neural Networks (Jannik Wildner)
Publications (Selection)
- R. Herdt, M. Schmidt, D. Otero Baguer, J. Le Clerc Arrastia, P. Maaß.
Model Stitching and Visualization How GAN Generators can Invert Networks in Real-Time.
Zur Veröffentlichung eingereicht.online at: https://arxiv.org/abs/2302.02181
- T. Lütjen, F. Schönfeld, J. Leuschner, M. Schmidt, A. Wald, T. Kluth.
Learning-based approaches for reconstructions with inexact operators in nanoCTapplications.
Zur Veröffentlichung eingereicht.online at: https://aps.arxiv.org/abs/2307.10474
- 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
- C. Arndt, A. Denker, J. Nickel, J. Leuschner, M. Schmidt, G. Rigaud.
In Focus - hybrid deep learning approaches to the HDC2021 challenge.
Inverse Problems and Imaging, , 2022.DOI: 10.3934/ipi.2022061
- R. Barbano, J. Leuschner, M. Schmidt, A. Denker, A. Hauptmann, P. Maaß, B. Jin.
An Educated Warm Start For Deep Image Prior-based Micro CT Reconstruction.
IEEE Transactions on Computational Imaging, 8:1210-1222, 2022.