Particle Physics meets Machine Learning

Seminar
QUEST Center event
No
Speaker
Jesse Thaler, MIT
Date
09/11/2020 - 20:00 - 17:55Add to Calendar 2020-11-09 17:55:00 2020-11-09 20:00:00 Particle Physics meets Machine Learning ZOOM LINK Meeting ID: 939 0317 8346 Passcode:326163 Add to Google Calendar Modern machine learning has had an outsized impat on many scientifc fields, and particle physics is no exception. What is special about particle physics, though, is the vast amount of theoretical and experimental knowelde that we already have about many problems in the field. In this colloquium, I present two case studies involving quantum chromodynamics (QCD), at the Large Hadron Collider (LHC) highlighting the fascinating interplay between theoretical principles and machine learning strategies. First, by catalogining the space of all possible QCD measurements, we (re)discoverd technology relevant for self-dricing cars. Second, by quantifying the similarity between two LHC collisions, we unlocked a class of nanparametric machine learining techniques based on optimal transport. In addition to providing new quantitative insights into QCD, these techniques enable new ways to visualize data from the LHC. Zoom Department of Physics physics.dept@mail.biu.ac.il Asia/Jerusalem public
Place
Zoom
Abstract

ZOOM LINK

Meeting ID: 939 0317 8346

Passcode:326163

Add to Google Calendar

Modern machine learning has had an outsized impat on many scientifc fields, and particle physics is no exception. What is special about particle physics, though, is the vast amount of theoretical and experimental knowelde that we already have about many problems in the field. In this colloquium, I present two case studies involving quantum chromodynamics (QCD), at the Large Hadron Collider (LHC) highlighting the fascinating interplay between theoretical principles and machine learning strategies. First, by catalogining the space of all possible QCD measurements, we (re)discoverd technology relevant for self-dricing cars. Second, by quantifying the similarity between two LHC collisions, we unlocked a class of nanparametric machine learining techniques based on optimal transport. In addition to providing new quantitative insights into QCD, these techniques enable new ways to visualize data from the LHC.

Attached file

Last Updated Date : 05/12/2022