BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Neural network representation of quantum systems - Koji Hashimoto 
 (Kyoto university)
DTSTART:20250326T140000Z
DTEND:20250326T144500Z
UID:TALK229645@talks.cam.ac.uk
CONTACT:Sven Krippendorf
DESCRIPTION:We provide a novel map with which a wide class of quantum mech
 anical systems can be cast into the form of a neural network with a statis
 tical summation over network parameters. Our simple idea is to use the uni
 versal approximation theorem of neural networks to generate arbitrary path
 s in the Feynman's path integral. The map can be applied to interacting qu
 antum systems / field theories\, even away from the Gaussian limit. Our fi
 ndings bring machine learning closer to the quantum world. The talk is bas
 ed on a collaboration with Y. Hirono\, J. Maeda and J. Totsuka-Yoshinaka\,
  https://arxiv.org/abs/2403.11420
LOCATION:DAMTP\, MR11
END:VEVENT
END:VCALENDAR