|Date||January 29, 2019||Time||4:00 - 5:00 pm|
|Location||Baylor Sciences Building, Room E.125|
Sergei Gleyzer, Ph.D.
The Large Hadron Collider (LHC) has achieved unprecedented levels of sensitivity to new particles at the TeV scale with searches for new physics including dark matter. This trend is expected to continue during the next LHC run in 2021 and with the upcoming upgrade to the LHC, the High-Luminosity Large Hadron Collider (HL-HLC), anticipated to start taking data in 2026. Additional complexity at the HL-LHC arises from a significant increase in pile-up, or additional particle collisions of protons traveling in the same bunch, leading to more complex event signatures. A new approach to event reconstruction and data analysis is required to address the challenges posed by the rarity of the sought-after signals, the unknown properties of physics processes, such as dark matter and the experimental challenges introduced by the high pile-up environment. In my talk, I will discuss how intelligent systems based on machine learning are used to select, reconstruct and analyze the data from the CMS experiment. I will discuss the application of new state-of-the-art data science methods, including modern deep learning methods, to physics challenges of the LHC and focus on the solutions they provide for the high-luminosity environment of HL-LHC. I will conclude by presenting significant new opportunities in the field of particle physics enabled by data science.
|Publisher||Department of Physics|
|vCal||Download this event|