BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:UW-Madison-Physics-Events
BEGIN:VEVENT
SEQUENCE:2
UID:UW-Physics-Event-8810
DTSTART:20250228T213000Z
DTEND:20250228T230000Z
DTSTAMP:20260413T202611Z
LAST-MODIFIED:20250217T040104Z
LOCATION:Chamberlin 2241
SUMMARY:Centaur Science: Particle Physics meets Machine Learning\, Phy
 sics Department Colloquium\, Jesse Thaler\, MIT
DESCRIPTION:Modern machine learning has had an outsized impact on many
  scientific fields\, and particle physics is no exception.  What is sp
 ecial about particle physics\, though\, is the vast amount of theoreti
 cal knowledge that we already have about many problems in the field\, 
 as well as the daunting deluge of data coming from flagship experiment
 s like the Large Hadron Collider (LHC).  In this colloquium\, I will e
 xplain how one can teach a machine to "think like a physicist" by embe
 dding theoretical principles into advanced machine learning architectu
 res.  At the same time\, I will advocate that physicists must learn ho
 w to "think like a machine" to maximize the physics reach of the LHC. 
  These joint developments are leading to a new kind of "centaur scienc
 e" that\, analogously to the mythical centaur\, draws half from partic
 le physics and half from machine learning.
URL:https://www.physics.wisc.edu/events/?id=8810
END:VEVENT
END:VCALENDAR