Choose timezone
Your profile timezone:
Machine Learning in CMS: New Approaches for High-Energy Physics Challenges
→
Europe/London
Berry Lecture Theatre
Berry Lecture Theatre
Description
The Compact Muon Solenoid (CMS) experiment at the Large Hadron Collider generates an unprecedented volume of complex data, posing unique challenges for effective analysis and interpretation. This seminar introduces state-of-the-art machine learning architectures, including Transformers and Normalizing Flows, and their innovative applications in high-energy physics. We will delve into their use in CMS for critical tasks such as detector reconstruction, precise calibration, fast simulation, and background estimation. The discussion will emphasize the transformative potential of these tools and the challenges encountered when adapting them to the demands of realistic particle physics problems.
This talk cannot cover the wide range of experiments done around the world using these incredible systems. My goal is, rather, to teach you what you need to know to understand the research done in the field. That is, I will briefly cover how one cools and traps atoms in light fields before describing the basics of quantum gas microscopy, as well as some of the limitations and challenges of microscopy-based quantum simulators. The last bit of the tutorial will comprise a whirlwind overview of some of the recent work being done on the study of systems relevant to quantum simulations (even of things like high-energy/particle physics!), giving the interested reader the foundation needed to learn more and some relevant literature with which to start.
