Research
ELLIS fosters international collaboration across domains, connecting top researchers while investing in the next generation of AI talent.
Members
ELLIS Members are leading scientists in machine learning and AI, shaping Europe's global position in these fields.
About
ELLIS is a pan-European AI network of excellence built upon machine learning as the driver for modern AI.
Uros Zivanovic
PhD
Max Planck Institute for Intelligent Systems (MPI-IS)
University of Tübingen
Machine learning (ML) has become an established tool for gravitational-wave (GW) data analysis. However, existing ML methods sometimes fail to produce accurate results, for example when analyzing data contaminated with detector noise glitches. In this project, we aim to address such limitations through new methods with improved robustness and reliability. Specifically, we will explore self-supervised representation learning to identify glitches in GW measurements, and integrate known causal structures of the data generating process, using methods such as half sibling regression, to mitigate their effect.
Interdisciplinary Track
September 1st, 2026 - August 31st, 2029
Research
About
