BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Siu-Cheong Lau (Boston University)
DTSTART:20210706T160000Z
DTEND:20210706T170000Z
DTSTAMP:20260423T022623Z
UID:Geolis/52
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Geolis/52/">
 Kaehler geometry of quiver moduli in application to machine learning</a>\n
 by Siu-Cheong Lau (Boston University) as part of Geometria em Lisboa (IST)
 \n\n\nAbstract\nNeural network in machine learning has interesting similar
 ity with quiver representation theory.  In this talk\, I will build an alg
 ebro-geometric formulation of a `computing machine'\, which is well-define
 d over the moduli space of representations.  The main algebraic ingredient
  is to extend noncommutative geometry of Connes\, Cuntz-Quillen\, Ginzburg
  to near-rings\, which capture the non-linear activation functions in neur
 al network.  I will also explain a uniformization between spherical\, Eucl
 idean and hyperbolic moduli of framed quiver representations.\n
LOCATION:https://researchseminars.org/talk/Geolis/52/
END:VEVENT
END:VCALENDAR