BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20200129T163603Z
LOCATION:502-503-504
DTSTART;TZID=America/Denver:20191117T112000
DTEND;TZID=America/Denver:20191117T114500
UID:submissions.supercomputing.org_SC19_sess101_ws_dls110@linklings.com
SUMMARY:Deep Learning Accelerated Light Source Experiments
DESCRIPTION:Workshop\n\nDeep Learning Accelerated Light Source Experiments
 \n\nLiu, Bicer, Kettimuthu, Foster\n\nExperimental protocols at synchrotro
 n light sources typically process and validate data only after an experime
 nt has completed, which can lead to undetected errors and cannot enable on
 line steering.  Real-time data analysis can enable both detection of, and 
 recovery from, errors, and optimization of data acquisition. However, mode
 rn scientific instruments, such as detectors at synchrotron light sources,
  can generate data at GBs/sec rates. Data processing methods such as the w
 idely used computational tomography usually require considerable computati
 onal resources, and yield poor quality reconstructions in the early stages
  of data acquisition when available views are sparse. \n\nWe describe here
  how a deep convolutional neural network can be integrated into the real-t
 ime streaming tomography pipeline to enable better-quality images in the e
 arly stages of data acquisition. Compared with conventional streaming tomo
 graphy processing, our method can significantly improve tomography image q
 uality, deliver comparable images using only 32% of the data needed for co
 nventional streaming processing, and save 68% experiment time for data acq
 uisition.\n\nTag: Workshop Reg Pass, Deep Learning, Scientific Computing\n
 \nRegistration Category: Workshop Reg Pass, Deep Learning, Scientific Comp
 uting
URL:https://sc19.supercomputing.org/presentation/?id=ws_dls110&sess=sess10
 1
END:VEVENT
END:VCALENDAR