Neural network representation of quantum systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hashimoto, Koji, Hirono, Yuji, Maeda, Jun, Totsuka-Yoshinaka, Jojiro
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909139676954624
author Hashimoto, Koji
Hirono, Yuji
Maeda, Jun
Totsuka-Yoshinaka, Jojiro
author_facet Hashimoto, Koji
Hirono, Yuji
Maeda, Jun
Totsuka-Yoshinaka, Jojiro
contents It has been proposed that random wide neural networks near Gaussian process are quantum field theories around Gaussian fixed points. In this paper, we provide a novel map with which a wide class of quantum mechanical systems can be cast into the form of a neural network with a statistical summation over network parameters. Our simple idea is to use the universal approximation theorem of neural networks to generate arbitrary paths in the Feynman's path integral. The map can be applied to interacting quantum systems / field theories, even away from the Gaussian limit. Our findings bring machine learning closer to the quantum world.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11420
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Neural network representation of quantum systems
Hashimoto, Koji
Hirono, Yuji
Maeda, Jun
Totsuka-Yoshinaka, Jojiro
High Energy Physics - Theory
Disordered Systems and Neural Networks
Artificial Intelligence
Machine Learning
Quantum Physics
It has been proposed that random wide neural networks near Gaussian process are quantum field theories around Gaussian fixed points. In this paper, we provide a novel map with which a wide class of quantum mechanical systems can be cast into the form of a neural network with a statistical summation over network parameters. Our simple idea is to use the universal approximation theorem of neural networks to generate arbitrary paths in the Feynman's path integral. The map can be applied to interacting quantum systems / field theories, even away from the Gaussian limit. Our findings bring machine learning closer to the quantum world.
title Neural network representation of quantum systems
topic High Energy Physics - Theory
Disordered Systems and Neural Networks
Artificial Intelligence
Machine Learning
Quantum Physics
url https://arxiv.org/abs/2403.11420