BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Miguel Crispim Romao - Artificial Intelligence and Machine Learnin
 g for Collider and Beyond the Standard Model Physics - Miguel Crispim Roma
 o (Southampton U. and LIP\, Minho)
DTSTART:20230203T160000Z
DTEND:20230203T170000Z
UID:TALK194926@talks.cam.ac.uk
CONTACT:Maeve Madigan
DESCRIPTION:In recent years\, High Energy Physics (HEP) has seen a resurge
 d interest in Artificial Intelligence and Machine Learning (AI/ML)\, drive
 n by the current renaissance of these fields. Whilst most of the AI/ML app
 lications in HEP have been developed in an experimental context\, there is
  a wealth of unexplored ideas for the application of AI/ML to phenomenolog
 ical and theoretical studies. \n\nIn this talk\, I will discuss some of ou
 r recent work on applying AI/ML to Collider and Beyond the Standard Model 
 (BSM) Physics. For the Collider applications\, I will focus on the efforts
  to isolate jets that have interacted with the Quark-Gluon Plasma\, an ess
 ential task to enable using jets as a probe for medium properties. I will 
 then discuss the application of AI/ML algorithms for BSM model building\, 
 with a particular focus on black box search algorithms to find valid multi
 dimensional parameter space regions of highly constrained models\, where r
 andom sampling efficiency can be prohibitively low.
LOCATION:Potter Room (B1.19)
END:VEVENT
END:VCALENDAR