BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Michael R. Douglas (Simons Center for Geometry and Physics)
DTSTART:20220412T150000Z
DTEND:20220412T160000Z
DTSTAMP:20260423T022626Z
UID:Geolis/80
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Geolis/80/">
 Holomorphic feedforward networks</a>\nby Michael R. Douglas (Simons Center
  for Geometry and Physics) as part of Geometria em Lisboa (IST)\n\n\nAbstr
 act\nA very popular model in machine learning is the feedforward neural ne
 twork (FFN). After a brief introduction to machine learning\, we describe 
 FFNs which represent sections of holomorphic line bundles on complex manif
 olds\, and software which uses them to get numerical approximations to Ric
 ci flat Kähler metrics.\n
LOCATION:https://researchseminars.org/talk/Geolis/80/
END:VEVENT
END:VCALENDAR