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:20230124T171520Z
LOCATION:C143-149
DTSTART;TZID=America/Chicago:20221113T110500
DTEND;TZID=America/Chicago:20221113T111500
UID:submissions.supercomputing.org_SC22_sess426_ws_isav101@linklings.com
SUMMARY:In Situ Monitoring and Steering Deep Learning Training from Numeri
 cal Simulations in ParaView-Catalyst
DESCRIPTION:Workshop\n\nIn Situ Monitoring and Steering Deep Learning Trai
 ning from Numerical Simulations in ParaView-Catalyst\n\nRibes, Mazen, Meye
 r\n\nIn the context of numerical simulation, a surrogate model approximate
 s the outputs of a solver with a low computational cost. In this article, 
 we present an In Situ visualization prototype, based on Catalyst 2, for mo
 nitoring the training of surrogate models based on Deep Neural Networks. W
 e believe that In Situ monitoring can help solve a fundamental problem of 
 this kind of training: standard metrics, such as the Mean Squared Error, d
 o not convey enough information on which simulation aspects are harder to 
 learn. Our prototype allows the interactive visualization of the current s
 tate of convergence of a physical quantity spatial field, complementing th
 e traditional loss function value curve. We enable the steering of physica
 l parameters during the training process, for interactive exploration. We 
 also allow the user to influence the learning process in real-time by chan
 ging the learning rate. Results are illustrated on a Computational Fluids 
 Dynamics use case.\n\nSession Format: Recorded\n\nTag: Accelerator-based A
 rchitectures, Data Analytics, In Situ Processing, Scientific Computing, Vi
 sualization, Workflows\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR
