Powered by Indico
v3.2.9
At the CERN Large Hadron Collider (LHC), real-time event filtering systems must process millions of proton-proton collisions every second on field programmable gate arrays (FPGAs) and perform efficient reconstruction and decision making. Within a few microseconds, over 98% of the collision data must be discarded fast and accurately. As the LHC is upgraded to its high luminosity phase, HL-LHC, these systems must deal with an overwhelming data rate corresponding to 5% of the total internet traffic and will face unprecedented data complexity. In order to ensure data quality is maintained such that meaningful physics analyses can be performed, ultrafast ML algorithms are being utilized for data processing. In the CMS Experiment, we expect to perform over 20 billion machine learning (ML) inferences per second during HL-LHC data taking.
In this seminar, we will discuss how real-time ML is used to process and filter the enormous amount of data in LHC experiments in order to improve physics acceptance. We will discuss state-of-the-art techniques for designing and deploying ultrafast ML algorithms on FPGA hardware. Finally, we will explore applications of real-time inference in particle physics experiments.
Thea Klaeboe Aarrestad is a Research Fellow at ETH Zürich and a member of the CMS Collaboration at CERN. Her research centers on how Machine Learning can be applied to particle physics problems, especially focusing on utilizing real-time ML for discovering new physics phenomena. She received her Ph.D. in Physics from the University of Zürich and spent two years as a Research Fellow at CERN before moving to Zürich as an SNSF Ambizione grantee.