The past decade was marked by an exponential increase in the availability of experimental data in high energy physics, leading to unprecedented precision in the description of particle interactions. However, indirect evidence for new physics processes, such as the existence of dark matter, motivates the development of new methodologies to scrutinize the data in the search for new scientific discoveries. In this talk, I will introduce different applications of how artificial intelligence (AI) has been transformative in the way to analyse data from collider experiments. These include the development of fast simulation routines, high-dimensional deconvolution algorithms, and alternative ways to search new particle interactions. I will discuss future directions for each of these areas and potential synergies with other fields in the physical sciences.
Biography:
Dr. Mikuni is a NESAP for Learning Postdoctoral Fellow at NERSC. His current research focuses on machine learning development and application for experimental High Energy Physics, including Likelihood-free deep learning for detector simulation, unfolding, and anomaly detection on the search for new physics processes. He received his PhD in 2021 from the University of Zurich, measuring the production cross-section of top quark pairs in association to b quarks and the search for new physics in signatures involving third-generation fermions using the data collected by the CMS Collaboration. (Source)
Cory 373