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:20190614T113000
DTEND;TZID=Europe/Stockholm:20190614T120000
UID:submissions.pasc-conference.org_PASC19_sess165_msa294@linklings.com
SUMMARY:Advanced Reconstruction and Pattern Recognition in HEP
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics, Physi
 cs\n\nAdvanced Reconstruction and Pattern Recognition in HEP\n\nSalzburger
 \n\nMachine learning (ML) and Data science has seen a recent boost with gl
 obal players, such as Google, Facebook or Amazon have surpassed in many as
 pects, e.g. data quantity and algorithmic complexity the requirements of l
 arge scale HEP experiments. On the other hand, the upcoming challenges for
  the high luminosity upgrade of the LHC or future experiments will require
  drastic improvement to the computational efficiency in order to fit withi
 n projected computing budget. While ML inspired/grounded techniques have b
 een successfully applied in HEP classification applications for quite some
  time, the computational most expensive event reconstruction has only rece
 ntly seen first attempts to replace classical pattern recognition algorith
 ms with advanced ML techniques. In this contribution, the current state of
  the art reconstruction will be reviewed and an overview of ML modules and
  their performance estimates in realistic event reconstruction setups of H
 EP experiments will be presented.
END:VEVENT
END:VCALENDAR