Abstract: Particle, nuclear, and astrophysics experiments are producing massive amounts of data to answer fundamental questions about the basic constituents of our universe. While researchers in these areas have been using advanced data science tools for decades, modern machine learning has introduced a paradigm shift whereby data can be directly analyzed holistically without first compressing it into a more manageable and human understandable format. How will the machines help us explore the unknown? Can they be trusted to give us the right answers? I’ll attempt to address these questions and others with a talk about the use of modern machine learning, including generative AI, in the study of fundamental interactions.
About the speaker: Dr. Benjamin Nachman is a staff scientist in the Physics Division at Lawrence Berkeley National Laboratory in Berkeley, California. His research focuses on the use of cutting-edge machine learning for data analysis in particle physics. He is a member of the ATLAS collaboration, an experiment using the Large Hadron Collider at CERN.