BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190719T085745Z
LOCATION:HG E 3
DTSTART;TZID=Europe/Stockholm:20190614T120000
DTEND;TZID=Europe/Stockholm:20190614T123000
UID:submissions.pasc-conference.org_PASC19_sess165_msa223@linklings.com
SUMMARY:Deep Learning for Fast Detector Simulation
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics, Physi
 cs\n\nDeep Learning for Fast Detector Simulation\n\nVallecorsa\n\nThe High
  Energy Physics (HEP) community has a long tradition of using Machine Lear
 ning methods to solve tasks related, mostly, to the selection of interesti
 ng events over the overwhelming background produced at colliders. In recen
 t years, several studies, in different fields of science, industry and soc
 iety, have demonstrated the benefit of using Deep Learning (DL) to solve t
 ypical tasks related to data analysis. Building on these examples, many HE
 P experiments are now working on integrating DL into their workflows for d
 ifferent applications: from data quality assurance, to real-time selection
 , to simulation. In particular, Monte Carlo simulation is expected to repr
 esent one of the major challenges, in terms of computing resources, for th
 e High Luminosity LHC and alternative fast simulation solutions will be re
 quired. In this talk, we will present several studies on the use of Genera
 tive Models as potential alternatives to classical fast simulation. Initia
 l results are very promising: different levels of agreement to standard Mo
 nte Carlo have been reached. Most studies are now beyond the initial proto
 typing stage, and face new challenges related to detailed performance asse
 ssment, optimisation, computing resources and integration in the simulatio
 n framework.
END:VEVENT
END:VCALENDAR