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:20181221T160906Z
LOCATION:A2 Ballroom
DTSTART;TZID=America/Chicago:20181114T153000
DTEND;TZID=America/Chicago:20181114T170000
UID:submissions.supercomputing.org_SC18_sess466@linklings.com
SUMMARY:Gordon Bell Prize Finalist Session 1
DESCRIPTION:ACM Gordon Bell Finalist, Awards Presentation\n\n\n167-PFlops 
 Deep Learning for Electron Microscopy: From Learning Physics to Atomic Man
 ipulation\n\nPatton, Johnston, Young, Schuman, March...\n\nAn artificial i
 ntelligence system called MENNDL, which used 25,200 Nvidia Volta GPUs on O
 ak Ridge National Laboratory’s Summit machine, automatically designed an o
 ptimal deep learning network in order to extract structural information fr
 om raw atomic-resolution microscopy data. In a few hours, MENND...\n\n----
 -----------------\nA Fast Scalable Implicit Solver for Nonlinear Time-Evol
 ution Earthquake City Problem on Low-Ordered Unstructured Finite Elements 
 with Artificial Intelligence and Transprecision Computing\n\nIchimura, Fuj
 ita, Yamaguchi, Naruse, Wells...\n\nTo address problems that occur due to 
 earthquakes in urban areas, we propose a method that utilizes artificial i
 ntelligence (AI) and transprecision computing to accelerate a nonlinear dy
 namic low-order unstructured finite-element solver. The AI is used to impr
 ove the convergence of iterative solver ...\n\n---------------------\nExas
 cale Deep Learning for Climate Analytics\n\nKurth, Treichler, Romero, Mudi
 gonda, Luehr...\n\nWe extract pixel-level masks of extreme weather pattern
 s using variants of Tiramisu and DeepLabv3+ neural networks. We describe i
 mprovements to the software frameworks, input pipeline, and the network tr
 aining algorithms necessary to efficiently scale deep learning on the Piz 
 Daint and Summit system...\n
END:VEVENT
END:VCALENDAR