Niklas Koenen

2015-2018: studies mathematics at the University of Bremen (B.Sc.)
2018-2021: studies mathematics at the University of Bremen (M.Sc.)
Since February 2021: Research Associate at BIPS

Articles with peer review
Koenen N, Wright MN. Interpreting deep neural networks with the package innsight. Journal of Statistical Software. 2024;111(8):1-52.
https://doi.org/10.18637/jss.v111.i08
Conference proceedings
Koenen N, Wright MN. Toward understanding the disagreement problem in neural network feature attribution. In: Longo L, Lapuschkin S, Seifert C, editors. Explainable artificial intelligence. Second World Conference, xAI 2024. Volume 2155. Cham: Springer. 2024. S. 247-269.
https://doi.org/10.1007/978-3-031-63800-8_13
Koenen N, Wright MN, Maass P, Behrmann J. Generalization of the change of variables formula with applications to residual flows. Thirty-eighth international conference on machine learning (ICML) workshop on invertible neural networks, normalizing flows, and explicit likelihood models. 2021.
https://openreview.net/forum?id=msCiI5dejr
Presentations at scientific meetings/conferences
Koenen N, Wright MN. Interpreting deep neural networks with the R package innsight. 6. Konferenz der Deutschen Arbeitsgemeinschaft Statistik (DAGStat), 28. März-1. April 2022, Hamburg.
Posters at scientific meetings/conferences
Koenen N, Wright MN, Maass P, Behrmann J. Generalization of the change of variables formula with applications to residual flows. 38th International Conference on Machine Learning (ICML) Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (INNF+), 23 July 2021, online poster.

For further publications please follow this link:

Fall 2021/2022 Interpretable Machine Learning Exercise Sessions (University of Bremen)

The responsibility for the content of this page lies with Niklas Koenen.

Phone:

+49 (0)421 218-56-933

e-mail: