Is Attention Interpretation? A Quantitative Assessment On Sets
- Jonathan Haab
- Nicolas Deutschmann
- et al.
- 2022
- NeurIPS 2022
I am a Research Scientist at IBM Zurich working in the AI four Scientific Discovery group. My research revolves around building interpretable approaches to machine learning, understanding and applying techniques to make machine learning models more robust, and quantifying modelling uncertainties.
I am a theoretical physicist by training; I got my Master's degree in physics from the Ecole Normale Superieure de Lyon in France and went on to get a joint PhD from the Universities of Louvain in Belgium and Lyon, during which I also spent significant time at CERN. I then moved to Zurich for a postodoctoral fellowship at ETHZ, working on perturbative chromodynamics and Higgs boson physics.