Back to all members...
Jannik Kossen
PhD, started 2020

Jannik is a DPhil student in the OATML group supervised by Yarin Gal and Tom Rainforth. He is working on (mostly Bayesian) Deep Learning. More specifically, he is currently looking into active learning, semi-supervised learning, and attention. Previously, he has dabbled with structured probabilistic models for object- and physics-aware video prediction. He received an MSc in Physics from Heidelberg University and has spent time studying in Bremen, Padova, and at UCL. Jannik is interested in the societal and ethical implications of AI: He has co-authored a book explaining machine learning to a broad audience, discussed the ethics of AI at the Berlin-Brandenburg Academy of Sciences, and gathered real-world field experience at Bosch.