BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230124T171522Z
LOCATION:C144-145
DTSTART;TZID=America/Chicago:20221114T142000
DTEND;TZID=America/Chicago:20221114T143500
UID:submissions.supercomputing.org_SC22_sess462_ws_ai4s104@linklings.com
SUMMARY:Automated Continual Learning of Defect Identification in Coherent 
 Diffraction Imaging
DESCRIPTION:Workshop\n\nAutomated Continual Learning of Defect Identificat
 ion in Coherent Diffraction Imaging\n\nYildiz, Chan, Raghavan, Judge, Cher
 ukara...\n\nX-ray Bragg coherent diffraction imaging (BCDI) is widely used
  for materials characterization. However, obtaining X-ray diffraction data
  is difficult and computationally intensive. Here, we introduce a machine 
 learning approach to identify crystalline line defects in samples from the
  raw coherent diffraction data. To automate this process, we compose a wor
 kflow coupling coherent diffraction data generation with training and infe
 rence of deep neural network defect classifiers. In particular, we adopt a
  continual learning approach, where we generate training and inference dat
 a as needed based on the accuracy of the defect classifier instead of all 
 training data generated a priori. The results show that our approach impro
 ves the accuracy of defect classifiers while using much fewer samples of d
 ata.\n\nSession Format: Recorded\n\nRegistration Category: Workshop Reg Pa
 ss
END:VEVENT
END:VCALENDAR