My goal is to build machine learning models capable of approaching the performance of biological brains in terms of data-efficiency and robustness to perturbations and changes in their environment. Drawing inspiration from adaptation behaviour of biological systems, I study methods for domain adaptation and continual, multi-task and self-supervised learning.

I am member of the Max Planck International Research School for Intelligent School advised by Matthias Bethge in Tübingen and the ELLIS PhD & PostDoc program advised by Mackenzie Mathis at the Rowland Institute at Harvard and EPFL (from summer 2020).

I spend the past year working on self-supervised representation learning for speech processing with Michael Auli, Alexei Baevski and Ronan Collobert at Facebook AI Research in Menlo Park, CA. For my Master's thesis, I worked on Domain Adaptation in Brains and Machines with Matthias Bethge and Alexander Ecker at the Max Planck Institute for Intelligent Systems and University of Tübingen and Jakob Macke at TU Munich.

Aside from my research, I'm a strong supporter of exposing children to modern computer science topics early on during their school education. That's why I co-founded and advised IT4Kids to teach CS in elementary school, KI macht Schule to teach AI and Machine Learning fundamentals in high school and helped organizing the German National Competition in AI for high school students.

Interests

  • Domain Adaptation
  • Motor Adaptation
  • Self-Supervised Learning
  • Information Theory
  • Optimal Transportation Theory
  • Medical Imaging
  • Temporal Learning
  • Computational Neuroscience

Education & Research

  • PhD Candidate in Machine Learning and Neuroscience, from 2019

    Intl. Max Planck Graduate School for Intelligent Systems, Tübingen

  • AI Resident, Self-Supervised Learning for Speech Recognition, 2018 - 2019

    Facebook AI Research, Menlo Park, CA

  • MSc in Neuroengineering, 2016 - 2018

    Technical University of Munich

  • BSc in Electrical Engineering, Information Technology and Computer Engineering, 2013 - 2016

    RWTH Aachen University

News

Meetings, Workshops & Talks

Software

Press

Publications

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

Projects

KI macht Schule

KI macht Schule provides classes in AI & Machine Learning for German high school students

NeuBtracker

An Imaging Platform for Neurobehavioral Research

Biomodels Retreat

Establishing fruitful collaborations between biologists, computer scientists and mathematicians in a yearly one-week retreat.

MSNE Blog

M.Sc. Neuroengineering Student Blog with latest information about our study program and events.

Ecurie Aix eace04/05

Contributions include the design of electric control units

Campus Weggemeinschaft

Homepage der Campus Weggemeinschaft

IT4Kids

IT4Kids provides computer science classes to elementary school pupils - Providing software, teaching materials and easy communication …