• Our paper A primer on Motion Capture with Deep Learning appeared in the October issue of Neuron. Work with Alexander Mathis, Jessy Lauer and Mackenzie Mathis.
• Our paper on improving robustness against common corruptions as accepted for poster presentation at NeurIPS 2020.
• I joined Amazon Web Services in Tübingen on September 1st as a full-time Applied Science intern, advised by Matthias Bethge, Bernhard Schölkopf and Peter Gehler.
• Our team at KI macht Schule organized a four day AI & ML bootcamp for students; learn more at KI-Camp.de.
• Together with fellow doctoral students of the Tübingen AI Competence Center, I am organizing a one-day doctoral symposium in February.
• I joined the Mouse Motor Lab led by Mackenzie Mathis as an ELLIS PhD student. I’ll be working at the Rowland Institute at Harvard in February and March.
• I co-organized a course on quantum machine learning with Luisa Eck (LMU Munich) and Lucas Stoffl (TU Munich) at the CdE winter school 2020 in Kaub and Oberwesel, Germany. Course material will eventually become available at https://github.com/stes/qml.
• vq-wav2vec was accepted for poster presentation at ICLR 2020.
• We presented wav2vec: Unsupervised Pre-training for Speech Recognition at Interspeech 2019.

Meetings, Workshops & Talks

• ICML Workshop on Uncertainty & Robustness in Deep Learning: Oral presentation (5% acceptance), of our paper Improving robustness against common corruptions by covariate shift adaptation
• May 2020: Co-Organizer, Quantum Machine Learning Course (2nd edition), CdE Spring School (canceled due to COVID)
• May 2020: Invited Talk on self-supervised learning and computational creativity at a workshop on “Creativity 2.0” organized by fellows of the German Academic Scholarship Foundation, Tübingen. (postponed due to COVID)
• April 2020: ICLR 2020, poster presentation of our paper vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
• February 2020: 1st Tübingen Robust Learning Symposium (Co-Organizer)
• January 2020: I gave a talk about “Data-Driven Modelling using Machine Learning: Potentials in Climate Science” in Berlin
• January 2020: Co-Organizer, Quantum Machine Learning Course, CdE Winter School
• September 2019: wav2vec: Improving Speech Recognition with Unsupervised Pre-Training (Poster Presentation at Interspeech 2019, Graz)
• Dezember 2019: Workshop Poster Presentations at NeurIPS 2019, Montreal
• June 2018: 2nd Smart Start Student Retreat in Freiburg, with contributions from Smart Start Students and our invited speakers Michael Tangermann, Radoslaw Cichy and Stefan Rotter.
• May 2018: Course on Learning in Brains and Machines at the CdE Pfingstakademie 2018 (spring school).
• December 2017: Introductory talk on Unsupervised Learning at 15x4 Munich.
• Summer 2017: Co-Organizer for the Biomodels Retreat near Barcelona, Spain.

Software

• (available soon) Code for our paper Improving robustness against common corruptions by covariate shift adaptation.
• (vq-) wav2vec code and models released as part of fairseq
• PyTorch toolbox for Semi-supervised Adaptive Learning Across Domains (salad) for a fair and reproducible evaluation of current domain adaptation algorithms

Press

• wav2vec is presented at Facebook F8 2019. May 1, 2019.
• Facebook details wav2vec, an AI algorithm that uses raw audio to improve speech recognition. Venturebeat, Nov 5, 2019.

I am always looking for motivated students interested in joining me in the Bethge and/or Mathis lab. If you’re interested in working with me on topics around robustness, domain adaptation, reinforcement learning and self-supervised learning at the intersection of neuroscience and machine learning, please contact me at steffen@bethgelab.org.

I am currently working with:

• Shubham Krishna started as a research assistant in the Bethge lab. Shubham works on topics around invariant representation learning and pruning techniques to better understand adaptation mechanisms in DNNs.
• Khushdeep Singh joined the Bethge lab as a Master thesis student in April. Khushdeep works on benchmarking and improving the robustness of reinforcement learning algorithms.
• Jin Hwa Lee joined the Bethge & Mathis labs in September. Jin is building self-supervised representation learning algorithms for analyzing neuroscience datasets.
• Xingying Chen joined mid september as a summer intern in the Bethge & Mathis labs. Xingying is modeling adaptation paradigms in neuroscience using reinforcement learning.
• Jan Hansen-Palmus from the Bringmann group at Uni Tübingen is co-advised by Evgenia Rusak and me. Jan writes his Bachelor’s thesis on pseudo-labeling approaches for unsupervised domain adaptation.

In the past, I also worked with:

• Mert Yüksekgönül (now visiting researcher in Poggio & Sinha Labs at MIT). Mert worked on 3D lifting approaches for analyzing behavioral data.

A full and up-to-date list is also available on Google Scholar.