Basics and Contact
- Machine Learning (especially unsupervised/generative models) for molecular systems
- Best paper award at ICLR 2018 for “Spherical CNNs”
- Graduation cum laude (distinction degree, MSc)
- Graduation with distinction (BSc)
Up to date list can be found on: https://scholar.google.de/citations?user=WNlTdm0AAAAJ&hl=en
- “Spherical CNNS”; Taco Cohen*, Mario Geiger*, Jonas Koehler*, Max Welling, International Conference on Learning Representations (ICLR); 2018; * equal contribution.
- “DP-MAC: The differentially private method of auxilliary coordinates for deep learning”; Frederik Harder, Jonas Koehler, Max Welling, Mijung Park; Workshop on Privacy Preserving Machine Learning (PPML) at the conference on Neural Information Processing Systems (NIPS/NeurIPS); 2018.
- “Convolutional Networks for Spherical Signals”; Taco Cohen, Mario Geiger, Jonas Koehler, Max Welling; Workshop on Principled Approaches to Deep Learning (PADL) at the International Conference on Machine Learning (ICML); 2017.
- “Cross-Domain Mining of Argumentative Text through Distant Supervision”; Khalid Al-Khatib, Henning Wachsmuth, Matthias Hagen, Jonas Koehler, Benno Stein; Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HTL); 2016.
Corporations/affiliations (e.g. previous projects, partnerships with industry):
- Merantix (https://www.merantix.com/applied-research/)
- Max-Planck Institute for Intelligent Systems, privacy-preserving machine learning group
Fine grained resume can be found on https://www.linkedin.com/in/jonaskoehler2/
- 01/2019 – now: PhD research on deep learning for molecular sciences at the group of Frank Noé, Freie Universität Berlin
- 01/2018 – 10/2018: Research internship at the Max-Planck Institute for Intelligent Systems, Tuebingen
- 09/2016 – 12/2018 MSc Artificial Intelligence, University of Amsterdam
- 04/2014 – 08/2016 BSc Computer Science, Bauhaus-University Weimar
- Before: studies in mathematics and theoretical physics (3 years), media art and electro-acoustic music (2 years), political sciences and economics (1 year)
What (e.g. experiences) shaped you as a researcher?
All models are wrong. Reality is random. Observations are noise.
What motivated you to do research in this field or specific project?
It is a nice field to follow my interests in applied math, algorithms and randomness.
What do you think is important in your field or research in general?
Beware of the ludic fallacy.
What helps you in your research?
Visual thinking, programming skills, a community of incredibly smart, helpful and encouraging peers.
What shapes you besides research? Do you have hobbies or volunteer work, which you want to share?
Make music (guitar, electronic), board games, food.