Prof. Dr. Dr. h.c. Peter Maaß
Leader of WG Industrial MathematicsHead of Center for Industrial Mathematics
Room: MZH 2250
Email: pmaass@math.uni-bremen.de
Phone: (0421) 218-63801
ORCID iD: 0000-0003-1448-8345
Email: pmaass@math.uni-bremen.de
Phone: (0421) 218-63801
ORCID iD: 0000-0003-1448-8345
Research Areas
- Inverse problems
- Machine learning
- signal and image analysis in life sciences
- computational engineering
- system theory and parameteridentifikation
Leader of Projects
- Design-KIT: Artificial Intelligence in mechanical component development; TP: Deep Learning for geometry generation of mechanical components (01.10.2020 - 31.03.2022)
- HYDAMO - Hybrid data-driven and model-based simulation of complex flow problems in the automotive industry (01.04.2020 - 31.03.2023)
- SPAplus: Small data problems in digital pathology and measures accompanying the programme (01.04.2020 - 31.03.2023)
- AGENS - Analytical-generative Networks for System Identification (01.04.2020 - 31.03.2023)
- DIAMANT - Digital Image Analysis and Imaging Mass Spectrometry to Differentiate Non-small Cell Lung Cancer (01.01.2020 - 31.12.2022)
- Studie zur Qualitätsbewertung, Standardisierung und Reproduzierbarkeit von Daten der bildgebenden MALDI-Massenspektrometrie – MALDISTAR (01.07.2019 - 30.06.2022)
- EU-ROMSOC: Project ''Data Driven Model Adaptations of Coil Sensitivities in MR Systems'' (01.11.2017 - 30.04.2021)
- BMBF-MPI²: Model-based parameter identification in magnetic particle imaging (01.12.2016 - 30.11.2019)
- DFG-Graduiertenkolleg: π³ Parameter Identification – Analysis, Algorithms, Applications (01.10.2016 - 31.03.2021)
- Neural networks in MALDI imaging (since 01.10.2016)
Courses (Selection)
- Mathematische Grundlagen des maschinellen Lernens (Sommersemester 2021)
- Nicht-linearen inversen Probleme: Analysis, Anwendungen und Algorithmen (Wintersemester 2020/2021)
- Oberseminar: Deep Learning, Inverse Probleme und Datenanalyse (Wintersemester 2020/2021)
- Funktionalanalysis (Sommersemester 2020)
- Oberseminar: Deep Learning, Inverse Probleme und Datenanalyse (Sommersemester 2020)
betreute/begutachtete Dissertationen (Selection)
- On deep learning applied to inverse problems - A chicken-and-egg problem (Sören Dittmer)
- Neural Networks for solving Inverse Problems. Applications in Materials Science and Medical Imaging (Daniel Otero Baguer)
- Recurrence Quantification Compared to Fourier Analysis for Ultrasonic Non-Destructive Testing of Fibre Reinforced Polymers” (Carsten Brandt)
- Double Backpropagation with Applications to Robustness and Saliency Map Interpretability (Christian Etmann)
- Principles of Neural Network Architecture Design:Invertibility and Domain-Knowledge (Jens Behrmann)
Theses (Selection)
- Using Neural Networks to Denoise CT Images (Rudolf Herdt)
- Out of Distribution Detection for Purity Assessment of Pellets using Neural Networks (Jannik Wildner)
- Differentiable architecture search - Fractional Kernel sizes in convolutional neural networks (Daniel Klosa)
- Invertible U-Nets for Memory-Efficient Backpropagation (Nick Heilenkötter)
- Application of Neural Networks For Solving Inverse Problems (Alexander Denker)
Patents
-
P. Maaß, J. H. Kobarg, F. Alexandrov, P. Vandergheynst, M. Goldabaee.
Verfahren zum rechnergestützten Verarbeiten von räumlich aufgelösten Hyperspektraldaten, insbesondere von Massenspektrometriedaten.
German Patent and Trade Mark Office DE102013207402A1,
Number of registration: 1020132074, Date of registration: 24.04.2013.
Published in patent bulletin no.: on 30.10.2014. -
P. Maaß, J. Oetjen, L. Hauberg-Lotte, F. Alexandrov, D. Trede.
Verfahren zur rechnergestützten Analyse eines oder mehrerer Gewebeschnitte des menschlichen oder tierischen Körpers.
German Patent and Trade Mark Office DE102014224916A1,
Number of registration: 1020142249, Date of registration: 04.12.2014.
Published in patent bulletin no.: on 06.09.2016.
US Patent & Trademark Office, US 20160163523 A1,
Anmeldenummer: 14/959967 , Anmeldedatum: 04.12.2014.
Veröffentlicht am 09.06.2016
Intellectual Property Office, GB 2535586,
Anmeldenummer: GB1521058.6, Anmeldedatum: 30.11.2015.
Veröffentlicht am 24.08.2016
Institut national de la propriété industrielle, FR 3029671 A1,
Anmeldenummer: FR1561774, Anmeldedatum: 03.12.2015.
Veröffentlicht am 10.06.2016 -
D. Trede, P. Maaß, H. Preckel.
Method for analysing the effect of a test substance on biological and/or biochemical samples.
US Patent and Trademark Office US2011/0098198 A1,
Number of registration: 2011009819, Date of registration: 29.04.2009.
Published in patent bulletin no.: PCT/EP09/55187 on 28.04.2011. -
D. Trede, P. Maaß, F. Alexandrov.
Verfahren und Vorrichtung zur rechnergestützten Verarbeitung eines digitalisierten Bildes sowie maschinenlesbarer Datenträger.
German Patent and Trade Mark Office 10 2011 003 242.8,
Number of registration: 102011003, Date of registration: 27.01.2011.
Published in patent bulletin no.: on 02.08.2012. -
D. Trede, P. Maaß, H. Preckel.
Verfahren zur Analyse der Wirkung einer Testsubstanz auf biologische und/oder biochemische Proben.
European Patent Office EP2128815,
Number of registration: 8155784, Date of registration: 07.05.2008.
Published in patent bulletin no.: 2009/49 on 02.12.2009. -
P. Maaß, A. K. Louis.
Verfahren und Vorrichtung zur dreidimensionalen Computertomographie.
German Patent and Trade Mark Office DE19623271A1,
Number of registration: 19623271, Date of registration: 31.05.1996.
Published in patent bulletin no.: 1997/49 on 04.12.1997. -
P. Maaß.
Verfahren zur Segmentierung von Zeichen.
German Patent and Trade Mark Office DE19533585C1,
Number of registration: 19533585, Date of registration: 01.09.1995.
Published in patent bulletin no.: 1997/02 on 09.01.1997.
Publications (Selection)
- T. Kluth, C. Bathke, M. Jiang, P. Maaß.
Joint super-resolution image reconstruction and parameter identification in imaging operator: Analysis of bilinear operator equations, numerical solution, and application to magnetic particle imaging.
Inverse Problems, 36 124006 36(12), 2020.online at: https://arxiv.org/abs/2004.13091
- S. Dittmer, C. Schönlieb, P. Maaß.
Ground Truth Free Denoising by Optimal Transport.
Zur Veröffentlichung eingereicht.online at: https://arxiv.org/abs/2007.01575
- S. Dittmer, T. Kluth, M. Henriksen, P. Maaß.
Deep image prior for 3D magnetic particle imaging: A quantitative comparison of regularization techniques on Open MPI dataset.
Zur Veröffentlichung eingereicht.online at: https://arxiv.org/abs/2007.01593
- A. Denker, M. Schmidt, J. Leuschner, P. Maaß, J. Behrmann.
Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction.
ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, 18.07-18.07.2020, Vienna, Austria.
online at: https://invertibleworkshop.github.io/accepted_papers/index.html
- T. Boskamp, D. Lachmund, R. Casadonte, L. Hauberg-Lotte, J. H. Kobarg, J. Kriegsmann, P. Maaß.
Using the chemical noise background in MALDI mass spectrometry imaging for mass alignment and calibration.
Analytical Chemistry, 92(1):1301-1308, 2020.DOI: 10.1021/acs.analchem.9b04473
online at: https://doi.org/10.1021/acs.analchem.9b04473