BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The Representation Theory of Neural Networks - Marco Armenta (Univ
 ersité de Sherbrooke)
DTSTART:20211203T160000Z
DTEND:20211203T170000Z
UID:TALK165142@talks.cam.ac.uk
DESCRIPTION:In this talk\, I will present how the representation theory of
  quivers can be used to study artificial neural networks. We will start by
  looking at why neural networks are pairs of a quiver representation and a
 n activation function and how a neural network computes an output for a gi
 ven input. We will then translate the computations of a neural network int
 o a quiver representation and show how these induced quiver representation
 s can be viewed inside a moduli space and finally how the training dynamic
 s of a neural network can be translated to this moduli space.
LOCATION:Seminar Room 2\, Newton Institute
END:VEVENT
END:VCALENDAR