CAPS Seminar: Black Boxes or Interpretable Models? Applications of Machine Learning, Symmetries, and Domain Knowledge to High-Dimensional Problems in Particle Physics

Event Type

Seminar/Symposium

Sponsor

Center for AstroPhysical Surveys

Location

NCSA - 1205 W Clark St, Urbana - RM 1040

Date

Sep 15, 2023   12:00 - 1:00 pm  

Speaker

Prof. David Miller

Contact

Srinivasan Raghunathan

E-Mail

srinirag@illinois.edu

Views

39

Originating Calendar

Center for AstroPhysical Surveys

Title: Black Boxes or Interpretable Models? Applications of Machine Learning, Symmetries, and Domain Knowledge to High-Dimensional Problems in Particle Physics.

Speaker: David W. Miller, UChicago

Abstract: The world of artificial intelligence (AI) and machine learning (ML) has undergone what some scientists refer to as the "3rd Age of AI” due to the confluence of developments in Algorithms, Computing Resources, and Big Data. Particle Physics has benefitted from, and in many ways strengthened and advanced, progress in AI/ML for decades due to its proliferation of enormous data sets, complex instrumentation, and enormous computing infrastructure. However, there exist both known and unknown deficiencies in our ability to explain “why” some AI/ML models yield a certain result. In this talk, I will discuss some of the context and applications of AI/ML in experimental particle physics. I will then focus on a few projects ongoing in my group that we believe target important problems relevant to the use of machine learning, symmetries, and domain knowledge in particle physics.