BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20220812T074334Z
LOCATION:Sydney Room
DTSTART;TZID=Europe/Stockholm:20220627T160000
DTEND;TZID=Europe/Stockholm:20220627T163000
UID:submissions.pasc-conference.org_PASC22_sess127_msa144@linklings.com
SUMMARY:The Maelstrom Protocol - Workflow for the Development of AI on HPC
DESCRIPTION:Minisymposium\n\nThe Maelstrom Protocol - Workflow for the Dev
 elopment of AI on HPC\n\nEmmerich\n\nOne of the challenges of today’s mach
 ine learning (ML) workflows lies in the storage and exchange of machine le
 arning models. Apart from these collaborative issues, running machine lear
 ning applications for training or prediction on HPC infrastructure is not 
 standardized. With Maelstrom, we undertake an effort to provide a protocol
  that allows collaboration on ML models, including data provenance. Furthe
 r, we provide an abstract interface to the infrastructure used, such that 
 a model can be compared on or distributed to several HPC clusters. Here, w
 e relate our protocol to the MLflow initiative.\n\nDomain: Climate, Weathe
 r and Earth Sciences, Computer Science and Applied Mathematics, Engineerin
 g, Physics
END:VEVENT
END:VCALENDAR