Kaehler geometry of quiver moduli in application to machine learning

Abstract: Neural network in machine learning has interesting similarity with quiver representation theory. In this talk, I will build an algebro-geometric formulation of a `computing machine', which is well-defined 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 neural network. I will also explain a uniformization between spherical, Euclidean and hyperbolic moduli of framed quiver representations.

algebraic geometrydifferential geometrysymplectic geometry

Audience: researchers in the topic

( video )

Geometria em Lisboa (IST)

Series comments: To receive the series announcements, which include the
Zoom access password*, please register in
math.tecnico.ulisboa.pt/seminars/geolis/index.php?action=subscribe#subscribe
*the last announcement for a seminar is sent 5 hours before the seminar.

Geometria em Lisboa video channel: educast.fccn.pt/vod/channels/bu46oyq74