Transforming Particle Physics with Machine Learning

by Prof. Tilmann Plehn (University of Heidelberg)

Thursday 28 May 2026, 16:15 → 17:30 Europe/Brussels

CYCL01 (Marc de Hemptinne (chemin du Cyclotron, 2, Louvain-la-Neuve))

Program:
16:15 Colloquium talk by Tilman Plehn
17:15 Open Q&A session
17:30 Drinks & Snacks with the speaker in the Cyclofette

Abstract:
Machine learning is not only transforming our lives, but also the way we do (particle) physics. I will describe a few key aspects of ML applications in particle physics, defining something like physics-specific representation learning. I will then give examples how we can use learned representations to improve network performance, include networks in a statistical framework, and understand what they learn. Finally, I will briefly show how an agentic interface to ML-simulations re-defines the way we do numerical simulations.