About me

I am an independent researcher currently supported by the UK AI Security Institute and Iliad. My current research focuses on ReLU neural networks as a testbed for deep learning theories and interpretability practice.

Previously, I was a postdoc at the Institute for Machine Learning at JKU Linz with Johannes Brandstetter and Sepp Hochreiter, where I worked with machine learning for geometry and simulation.

I received a PhD in mathematics from the University of Oslo for the thesis on Neural Representations in Geometry. I was hosted by the Geometry group at SINTEF as a fellow of GRAPES — a Marie Sklodowska-Curie ITN on Learning, processing and optimising shapes.

I received my BSc and MSc in mechanical engineering from RWTH Aachen specializing in simulation technology and applying machine learning to geometry-heavy engineering tasks. Some of my research interests include

• geometry in ML,
• interpretability,
• ReLU neural networks,
• ML for science and engineering.