BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Marco Armenta
DTSTART:20210120T150000Z
DTEND:20210120T160000Z
DTSTAMP:20260423T004656Z
UID:TRAC/3
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/TRAC/3/">The
  representation theory of neural networks</a>\nby Marco Armenta as part of
  The TRAC Seminar - Théorie de Représentations et ses Applications et Co
 nnections\n\n\nAbstract\nIn this talk I will present recent applications o
 f representation theory to the study of neural networks in artificial inte
 lligence. First\, a neural network can be taken as a representation-like o
 bject to which we can apply isomorphisms of quiver representations that pr
 eserve what a neural network computes. Second\, we can encode the decision
 s and computations of a neural network on a single sample of data in terms
  of a stable double-framed thin quiver representation\, and since the outp
 ut of a neural network is independent of the representative in the isomorp
 hism class\, it makes sense to consider these "data quiver representations
 " in a moduli space of stable thin representations.\n
LOCATION:https://researchseminars.org/talk/TRAC/3/
END:VEVENT
END:VCALENDAR