PhD position on analysis of geometric machine learning methods

We are looking for a motivated, theory-oriented PhD candidate 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. A precise understanding of these aspects will be linked to their impact on stability and the understanding of spectral biases in graph neural networks.

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.

Are you interested in this position? Please send your application via the 'Apply now' button below before April 16th 2024, and include:

• A motivation letter, emphasizing your specific interest and motivation to apply for a PhD position in this research area.
• A detailed Curriculum Vitae.
• An academic transcript of BSc and MSc education, including grades.
• A summary of your MSc thesis/final project.
• References (contact information) of two  scientific staff members (preferably including the supervisor of your MSc thesis/final project) who are willing to provide a recommendation letter at our request.

For more information regarding this position, you are welcome to contact Dr. rer. nat. José A. Iglesias Martínez ([email protected])

The faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) uses mathematics, electronics and computer technology to contribute to the development of Information and Communication Technology (ICT). With ICT present in almost every device and product we use nowadays, we embrace our role as contributors to a broad range of societal activities and as pioneers of tomorrow's digital society. As part of a people-first tech university that aims to shape society, individuals and connections, our faculty works together intensively with industrial partners and researchers in the Netherlands and abroad, and conducts extensive research for external commissioning parties and funders. Our research has a high profile both in the Netherlands and internationally. It has been accommodated in three multidisciplinary UT research institutes: Mesa+ Institute, TechMed Centre and Digital Society Institute.