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:20211207T055400Z
LOCATION:Online
DTSTART;TZID=America/Chicago:20211115T080000
DTEND;TZID=America/Chicago:20211115T170000
UID:submissions.supercomputing.org_SC21_sess192_tut144@linklings.com
SUMMARY:Scientific Machine Learning Using HPC Servers on the Cloud
DESCRIPTION:Tutorial\n\nScientific Machine Learning Using HPC Servers on t
 he Cloud\n\nAdavani, Ganapathysubramanian, Balu, Chappell, Botelho...\n\nA
  comprehensive overview of building and deploying neural forward and inver
 se PDE solvers will be presented. We will discuss Physics-Informed Neural 
 Networks (PINNs), which are usually dense networks producing point-wise so
 lutions of PDEs, as well as CNN-based networks for producing full-field so
 lutions of parametric PDEs, along with GAN-based networks that solve both 
 forward and inverse ODEs. We will work through several cloud scalable appr
 oaches including those for simulating across parameters, as well as distri
 buted deep-learning to obtain high-fidelity solutions. This hands-on tutor
 ial will provide the theoretical background, computational training and so
 ftware tools for practitioners to rapidly deploy cloud scalable solutions 
 for their forward and inverse PDE needs. We will provide access to Microso
 ft Azure HPC clusters, and scripts for attendees to follow all demos at th
 eir own pace. We envision this tutorial to be of significant utility for a
 cademic and industry practitioners interested in the seamless scale-up of 
 their approaches.\n\nTag: Online Only, AI-HPC Convergence\n\nRegistration 
 Category: Tutorial Reg Pass
END:VEVENT
END:VCALENDAR