Erik Jenner

Erik Jenner

AI Master’s Student

University of Amsterdam

Hi there!

I’m a Master’s student in Artificial Intelligence at the University of Amsterdam. My goal is to have a positive impact on the world by making sure that AI will be aligned with humanity’s interests.

I’m currently working on my Master’s thesis with the Center for Human-Compatible AI on distance measures between reward functions. Before that, I have done work on the interpretability of reward models, equivariant deep learning, and on graph-based segmentation.

Interests
  • Reward Learning
  • Interpretability
  • Robust ML
Education
  • MSc in Artificial Intelligence, since 2020

    University of Amsterdam

  • BSc in Physics, 2020

    Heidelberg University

Research Experience

 
 
 
 
 
University of Amsterdam / UC Berkeley
Master’s thesis
Nov 2021 – Present Amsterdam
Working on distance measures between reward functions with Adam Gleave (UC Berkeley) and Prof. Herke van Hoof (UvA)
 
 
 
 
 
Center for Human-Compatible AI
Research Intern
Jul 2021 – Sep 2021 UC Berkeley (virtual)
  • Worked on interpretability of reward models together with Adam Gleave
  • Developed a method to simplify a given reward model while keeping it equivalent to the original
  • Published results at the NeurIPS Cooperative AI workshop
  • Implemented preference comparisons for the imitation library
 
 
 
 
 
QUVA Lab
Research Intern
Feb 2021 – Jun 2021 Amsterdam
  • Worked with Maurice Weiler (PhD student in Max Welling’s group)
  • Developed the theory of equivariant partial differential operators
  • Published a paper with my results at ICLR 2022
 
 
 
 
 
Heidelberg Collaboratory for Image Processing
Bachelor thesis
Apr 2020 – Jul 2020 Heidelberg
  • Supervised by Prof. Fred Hamprecht
  • Analyzed the extensibility of Karger’s contraction algorithm
  • Paper based on my thesis was accepted as an Oral at ICCV 2021