Dr. Christian Reimers
Curriculum Vitae
Research interests
- Machine learning
- Causal Modeling
- Statistical Learning Theory
Academic background
since 2021
2017-2021
and Climate Informatics Group, Institute of Data Science, German Aerospace Cen-
ter, Jena, Germany.
on the Topic of "Understanding Deep Learning"
2015-2016
Self-Organization, Göttingen.
2013-2017
Master thesis titel:"Almost Prime Zeros of Forms"
2011-2013
''Bachelor thesis title: "Hooley’s solution of a problem of Hardy
and Littlewood"''
Publications
2021
Reimers, C. and Bodesheim, P. and Runge, J. and Denzler J. (2021) Conditional Adversarial Debiasing: Towards Learning Unbiased Classifiers from Biased Data DAGM German Conference on Pattern Recognition (DAGM-GCPR). (accepted for publication)
Penzel, N., Reimers, C., Brust, C.-A. and Denzler, J. (2021) Investigating the Consistency of Uncertainty Sampling in Deep Active Learning DAGM German Conference on Pattern Recognition (DAGM-GCPR). (accepted for publication)
Tibau, X. A., Reimers, C., Requena‐Mesa, C., & Runge, J. (2021). Spatio‐temporal Autoencoders in Weather and Climate Research. Deep learning for the Earth Sciences: With Applications and R, Second Edition, 186-203.
Reimers, C., Penzel, N., Bodesheim, P., Runge, J and Denzler, J. (2021). Conditional dependence tests reveal the usage of ABCD rule features and bias variables in automatic skin lesion classification. CVPR ISIC Skin Image Analysis Workshop (CVPR-WS).
2020
Reimers, C, Runge, J and Denzler, J. (2020). Determining the Relevance of Features for Deep Neural Networks. ECCV
Reimers, C, Requena-Mesa, C. (2020). Deep Learning – an Opportunity and a Challenge for Geo- and Astrophysics. Knowledge Discovery in Big Data from Astronomy and Earth Observation
2019
Reimers, C, Runge, J , Denzler, J. (2019) Using Causal Inference to Globally Understand Black Box Predictors Beyond Saliency Maps. Climate Informatics Workshop 2019 proceedings.
2018
Tibau, X-A*, Requena-Mesa, C*, Reimers, C*, Denzler, J, Eyring, V, Reichstein, M and Runge, J. (2018) SupernoVAE: Using deep learning to find spatio-temporal dynamics in Earth system data. Climate Informatics Workshop 2018 proceedings.