BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Prague
BEGIN:DAYLIGHT
DTSTART:20250330T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251213T133415Z
UID:F9D1CDBF-CFF4-4FC5-8629-0FB9743F37A8
DTSTART;TZID=Europe/Prague:20250506T140000
DTEND;TZID=Europe/Prague:20250506T150000
DESCRIPTION:Spurious signals caused by microdischarges are a known effect i
 nherent to all gaseous detectors\, such as time projection chambers (TPC).
  During the reconstruction in imaging and tracking detectors\, these signa
 ls are added to the actual track-generated signal as extra pixels or clust
 ers\, compromising the performance of the detector. In order to denoise th
 ese artifacts\, we leveraged an existing technique\, which uses 2D convolu
 tional neural networks\, to denoise TPC events represented by 3D arrays. I
 n this seminar\, I will guide you through this process\, discussing the em
 erging challenges when real data are used instead of toy examples with cle
 an datasets.\n\nMatěj Gajdoš\n\nIEAP\, CTU in Prague\, Husova 240/5\, Pr
 ague\, Czech Republic\, Czech Republic
LOCATION:IEAP\, CTU in Prague\, Husova 240/5\, Prague\, Czech Republic\, Cz
 ech Republic
ORGANIZER:andre.sopczak@cern.ch
SEQUENCE:3
SUMMARY:TPC track denoising and recognition using convolutional neural netw
 orks
URL;VALUE=URI:https://events.vtools.ieee.org/m/522181
X-ALT-DESC:Description: &lt;br /&gt;&lt;p&gt;Spurious signals caused by microdischarges
  are a known effect inherent to all gaseous detectors\, such as time proje
 ction chambers (TPC). During the reconstruction in imaging and tracking de
 tectors\, these signals are added to the actual track-generated signal as 
 extra pixels or clusters\, compromising the performance of the detector. I
 n order to denoise these artifacts\, we leveraged an existing technique\, 
 which uses 2D convolutional neural networks\, to denoise TPC events repres
 ented by 3D arrays. In this seminar\, I will guide you through this proces
 s\, discussing the emerging challenges when real data are used instead of 
 toy examples with clean datasets.&lt;/p&gt;\n&lt;p&gt;Matěj Gajdo&amp;scaron\;&lt;/p&gt;\n&lt;p&gt;&amp;n
 bsp\;&lt;/p&gt;
END:VEVENT
END:VCALENDAR