Key information:
| Student | Kieran Maguire |
| Academic Supervisors |
Sri Dasmahapatra, Stefano Moretti, Claire Shepherd-Themistocleous, |
| Cohort | 3 |
| Pure Link | Active Project |
Particle physics aims at discovering the fundamental laws of matter and forces, informed by particle collisions produced at the Large Hadron Collider. Graph neural networks are trainable functions that operate on graphs - sets of elements and their pairwise relations - and are a central method within the broader field of geometric deep learning. Their expressivity has demonstrated superior performance to other classical deep learning approaches in a variety of domains. The data in particle physics is often represented in terms of graphs, and as such, geometry-aware graph neural networks offer a possible route to better interpret the results produced at the Large Hadron Collider.