PhD Position on Analysis of Geometric Machine Learning Methods, University of Twente
Deadline: 16 apr 2024
We are looking for a motivated, theory-oriented PhD candidate with an MSc degree in Mathematics, to work on the project "A continuum view on geometric deep learning".
In this project we aim to understand the transferability, mesh-independence and effect of symmetries on geometric learning approaches, in general and when applied to scenarios governed by (partial) differential equations on objects with geometric invariances.
The approach envisioned is based on discrete-to-continuum limits of models on densely sampled geometric graphs, combining approximation-theoretical, spectral and variational points of view.
The PhD candidate will work under the supervision of Dr. rer. nat. José A. Iglesias Martínez and prof. dr. Christoph Brune, as part of the group “Mathematics of Imaging and Artificial Intelligence” (MIA) at the Department of Applied Mathematics.