Prof. Dr. rer. nat. Ullrich Köthe

Professor for Computer Science
Head of Explainable Machine Learning research group
Co-Head of Visual Learning Lab
Heidelberg University

Explainable Machine Learning


1986 – 1991 Diploma studies in Physics, Rostock University, Germany
1991 Research Assistant, University Hospital, Rostock, Germany
1992 – 1999 Research Associate, Fraunhofer Institute for Computer Graphics, Rostock, Germany
1993 Guest Researcher at David Sarnoff Research Center, Princeton, USA
1999 – 2000 PhD Student, Cognitive Systems Lab, Hamburg University, Germany
2000 PhD (Dr. rer. nat.) in Computer Science, Hamburg University, Germany
2000 – 2007 Assistant Professor, Cognitive Systems Lab, Hamburg University, Germany
2004 Guest Researcher at the Computational Vision and Active Perception Laboratory, Royal Institute of Technology, Stockholm, and the Computer Vision Laboratory, Linköping University, Sweden
2008 Habilitation in Computer Science, Hamburg University, Germany
2007 – 2017 Vice Head of Image Analysis and Learning Lab, Heidelberg University, Germany
Since 2017 Head of Explainable Machine Learning research group
Co-Head of Visual Learning Lab, Heidelberg University, Germany
Since 2018 Adjunct Professor (außerplanmäßiger Professor) for Computer Science, Heidelberg University, Germany



Reviewer for 10+ Journals/conferences, including IEEE PAMI, International Journal on Computer Vision, Image and Vision Computing, Pattern Recognition Letters, GCPR, DGCI, ICCV, ECCV, CVPR

Program Committee Member for German Conference on Pattern Recognition (since 2007), Discrete Geometry for Computer Imagery (2009, 2011), Advanced Concepts for Intelligent Vision Systems (2005), International Conference on Computer Vision Theory and Applications (2006, 2007)

Head of Technical Committee 18 “Discrete Geometry” of the International Association for Pattern Recognition (2008-2011)

Organizer of workshop “Applications of Discrete Geometry and Mathematical Morphology” (2010) and International IWR Summer School ” Machine Learning with Applications in Natural- and Life Sciences” (2019)



Lecture “Fundamentals of Machine Learning” (2014, 2015, 2017, 2018)

Lecture “Advanced Machine Learning” (2015, 2016, 2018, 2019)

Lecture “Algorithms and Data Structures” (2008, 2012, 2014, 2017, 2020)

Lecture “Introduction to Computer Science” (2016)

Course “Introduction to Programming” (2009, 2014, 2015)

Course “A Crash Course in Machine Learning” (2019)

Tutorial “Normalizing Flows and Invertible Neural Networks in Computer Vision” (2020)

Seminars on “How do I lie with statistics?”, “Artificial intelligence for games”, “Explainable machine learning”, “Is artificial intelligence dangerous?”, “Algorithms for big data”



1993 Stipendium zur Förderung des wissenschaftlichen Nachwuchses in den neuen Bundesländern
2003 DAGM 2003 Main Prize
2008 DAGM 2008 Award (jointly with B. Andres, F. Hamprecht, M. Helmstädter, W. Denk)
2012 Machine Learning in Medical Imaging MLMI 2012 best paper award (jointly with X. Lou, L. Fiaschi, F. Hamprecht)
2013 DAGM 2013 Award (jointly with C. Strähle, F. Hamprecht)



Dr. Köthe has published >100 papers (h-index: 32, i10-index: 60, overall citation count: 3740; source: google scholar). See for a complete publication list.

List of ten representative publications:

1. Sorrenson P, Rother C, Köthe U: “Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)”, In: Intl. Conf. on Learning Representations (ICLR), arXiv:2001.04872, 2020

2. Ardizzone, L, Kruse, J, Wirkert, S, Rahner, D, Pellegrini, E W, Klessen, R S, Maier-Hein, L, Rother, C, and Köthe, U: “Analyzing inverse problems with invertible neural networks”, In: Intl. Conf. on Learning Representations (ICLR), arXiv:1808.04730, 2019

3. Radev, S T, Mertens, U K, Voss, A, and Köthe, U: “Towards end‐to‐end likelihood‐free inference with convolutional neural networks”, British Journal of Mathematical and Statistical Psychology, doi:10.1111/bmsp.12159, 2019

4. Berg, S, Kutra, D, Kroeger, T, Straehle, C N, Kausler, B X, Haubold, C, Schiegg, M, Ales, J, Beier, T, Rudy, M, Eren, K, Cervantes, J, Xu, B, Beuttenmueller, F, Wolny, A, Zhang, C, Koethe, U, Hamprecht, F A, and Kreshuk A: “ilastik: interactive machine learning for (bio) image analysis”, Nature Methods, doi:10.1038/s41592-019-0582-9, 2019

5. Wolf, S, Pape, C, Bailoni, A, Rahaman, N, Kreshuk, A, Köthe, U, and Hamprecht, F A: “The mutex watershed: efficient, parameter-free image partitioning”, In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 546-562, 2018

6. Andres, B, Kröger, T, Briggmann, K L, Denk, W, Norogod, N, Knott, G, Köthe, U and Hamprecht, F A: “Globally Optimal Closed-Surface Segmentation for Connectomics”. 12th Eur. Conf. Computer Vision (ECCV 2012), Springer LNCS 7574, pp. 778-791, 2012.

7. Sommer, C, Straehle, C N, Köthe, U, Hamprecht, F A: “ilastik: Interactive learning and segmentation toolkit”, 8th Intl. Symp. Biomedical Imaging (ISBI 2011), pp. 230-233, 2011.

8. Menze, B, Kelm, B H, Splitthoff, N, Köthe, U and Hamprecht, F A: “On oblique random forests”, Mach. Learning and Knowledge Discovery in Databases, Springer LNCS 6912, pp. 453-469, 2011.

9. Stelldinger, P, Köthe, U: “Towards a general sampling theory for shape preservation”, Image and Vision Computing, 23(2): 237-248, 2005.

10. Köthe, U: “Edge and Junction Detection with an Improved Structure Tensor”, in: B. Michaelis, G. Krell (Eds.): Proc. of 25th DAGM Symposium, Springer LNCS 2781, pp. 25-32, 2003.