Publikationen von Dr. Jens Behrmann
Buchkapitel (1)
- J. Behrmann, M. Schmidt, J. Wildner, P. Maaß, S. Schmale.
Purity Assessment of Pellets Using Deep Learning.
German Success Stories in Industrial Mathematics, H. Bock, K. Küfer, P. Maaß, A. Milde, V. Schulz (Hrsg.), Mathematics in Industry, S. 29-34, Springer Verlag, 2022.
Zeitschriftenartikel (2)
- C. Janßen, T. Boskamp, L. Hauberg-Lotte, J. Behrmann, S. Deininger, M. Kriegsmann, K. Kriegsmann, G. Steinbuß, H. Winter, T. Muley, R. Casadonte, J. Kriegsmann, P. Maaß.
Robust subtyping of non-small cell lung cancer whole sections through MALDI mass spectrometry imaging.
Proteomics - Clinical Applications, PRCA2208 , 2022. - J. Behrmann, C. Etmann, T. Boskamp, R. Casadonte, J. Kriegsmann, P. Maaß.
Deep Learning for Tumor Classification in Imaging Mass Spectrometry.
Bioinformatics, 34(7):1215-1223, Oxford University Press, 2018.
Preprints (3)
- J. Behrmann, P. Vicol, K. Wang, R. Grosse, J. Jacobsen.
Understanding and Mitigating Exploding Inverses in Invertible Neural Networks.
Zur Veröffentlichung eingereicht.online unter: https://arxiv.org/abs/2006.09347
- C. Etmann, M. Schmidt, J. Behrmann, T. Boskamp, L. Hauberg-Lotte, A. Peter, R. Casadonte, J. Kriegsmann, P. Maaß.
Deep Relevance Regularization: Interpretable and Robust Tumor Typing of Imaging Mass Spectrometry Data.
Zur Veröffentlichung eingereicht.online unter: https://arxiv.org/abs/1912.05459
- J. Behrmann, S. Dittmer, P. Fernsel, P. Maaß.
Analysis of Invariance and Robustness via Invertibility of ReLU-Networks.
Zur Veröffentlichung eingereicht.online unter: https://arxiv.org/abs/1806.09730
Qualifikationsarbeiten (1)
- J. Behrmann.
Principles of Neural Network Architecture Design: Invertibility and Domain Knowledge.
Dissertationsschrift, Universität Bremen, 2019.online unter: https://elib.suub.uni-bremen.de/peid/D00108536.html
Tagungsbeiträge (8)
- 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, Wien, Österreich.
online unter: https://invertibleworkshop.github.io/accepted_papers/index.html
- F. Tramer, J. Behrmann, N. Carlini, N. Papernot, J. Jacobsen.
Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations.
International Conference on Machine Learning (ICML), 12.07 - 18.07.2020, Wien, Österreich.
online unter: https://arxiv.org/abs/2002.04599
- J. Behrmann, P. Vicol, K. Wang, R. Grosse, J. Jacobsen.
On the Invertibility of Invertible Neural Networks.
NeurIPS workshop on Machine Learning with Guarantees, 2019.
online unter: https://sites.google.com/view/mlwithguarantees/accepted-papers
- J. Jacobsen, J. Behrmann, R. Zemel, M. Bethge.
Excessive Invariance Causes Adversarial Vulnerability.
International Conference on Learning Representations (ICLR), 2019.
online unter: https://openreview.net/forum?id=BkfbpsAcF7
- J. Jacobsen, J. Behrmann, N. Carlini, F. Tramer, N. Papernot.
Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness.
SafeML Workshop, ICLR, 2019.
online unter: https://arxiv.org/abs/1903.10484
- J. Behrmann, W. Grathwohl, R. T. Chen, D. Duvenaud, J. Jacobsen.
Invertible Residual Networks.
International Conference on Machine Learning (ICML).
Proceedings of Machine Learning Research, 97:573-582, 2019.Long Oral
online unter: http://proceedings.mlr.press/v97/behrmann19a.html
- R. T. Chen, J. Behrmann, D. Duvenaud, J. Jacobsen.
Residual Flows for Invertible Generative Modeling.
Advances in Neural Information Processing Systems (NeurIPS).
32, S. 9916--9926, 2019.Spotlight
online unter: https://papers.nips.cc/paper/9183-residual-flows-for-invertible-generative-modeling
- T. Boskamp, D. Lachmund, J. Oetjen, Y. Hernandez-Cordero, J. Behrmann, J. H. Kobarg, R. Casadonte, J. Kriegsmann, P. Maaß.
Visualizing MALDI TOF datasets of FFPE tissue samples for the purpose of quality assessment and comparison.
OurCon IV - 2016, 17.10.-21.10.2016, Ustron, Polen.
online unter: http://www.bioradint.eu/ourcon_public/papersview.php?showdetail=&paper_id=45