BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine-learning quantum gravity : a generative discrete geometry 
 and neural polytopes - Koji Hashimoto (Kyoto University)
DTSTART:20231106T143000Z
DTEND:20231106T153000Z
UID:TALK201799@talks.cam.ac.uk
DESCRIPTION:In this talk\, I discuss a possible way to perform quantum gra
 vity path integral by using machine learning. Our new model of generative 
 discrete geometry can provide a theoretical ground.&nbsp\;\nI start with e
 xplaining our machine-learning solver of quantum mechanics. Our proposed m
 ethod computes the wavefunctions in quantum mechanics using machine learni
 ng with unstructured deep neural networks (NNs). In the course\, we bridge
  discrete geometry and machine learning through the interpretation of the 
 obtained NN wavefunctions. As an application\, we find that a simple NN wi
 th ReLU activation generates polyhedra as an approximation of the unit sph
 ere in various dimensions. The type of polyhedron is controlled by the NN 
 architecture. For various activation functions\, a generalization of the p
 olyhedra is obtained\, which we name the neural polytopes. These are a smo
 oth generalization of polytopes and exhibits geometric duality. As NNs can
  generate discrete geometries\, combining this with the "NN=QFT" idea or t
 he traditional random NN idea\, we may formulate quantum gravity by miachi
 ne learning.
LOCATION:External
END:VEVENT
END:VCALENDAR