Jannik Kossen

Jannik Kossen

πŸ‘¨β€πŸ’» PhD Student in Machine Learning

🧠 OATML Oxford

Hi! πŸ‘‹

Thanks for stopping by!

I am a PhD student in the OATML group supervised by Yarin Gal and Tom Rainforth. I am working on (mostly Bayesian) Deep Learning. More specifically, I am currently looking into active learning, semi-supervised learning, and attention. Previously, I have dabbled with structured probabilistic models for object- and physics-aware video prediction. I received an MSc in Physics from Heidelberg University and have spent time studying in Bremen, Darmstadt, Padova, and at UCL.

I am interested in the societal and ethical implications of AI: I have 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.

πŸ“° News

All News»

07/21 - Invited talk at Cohere about Non-Parametric transformers.

06/21 – Selected as reviewer for ICLR 2022.

06/21 – I have decided to release my 2020 MSc thesis Modelling Videos of Physically Interacting Objects.

06/21 – Very excited to announce a new-preprint: Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning.

05/21 – Invited talk at AI Campus Berlin on Active Testing: Sample-Efficient Model Evaluation.

05/21 – Very excited to announce that Active Testing: Sample-Efficient Model Evaluation, my first paper at OATML Oxford, has been accepted for publication at ICML 2021.

04/21 – Selected as reviewer for NeurIPS 2021.

12/20 – Selected as reviewer for ICML 2021.

πŸ“« Contact