A Machine Learning Approach to Trapped Many-Fermion Systems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bedaque, Paulo F., Kumar, Hersh, Sheng, Andy
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909359725871104
author Bedaque, Paulo F.
Kumar, Hersh
Sheng, Andy
author_facet Bedaque, Paulo F.
Kumar, Hersh
Sheng, Andy
contents We apply a variational Ansatz based on neural networks to the problem of spin-$1/2$ fermions in a harmonic trap interacting through a short distance potential. We showed that standard machine learning techniques lead to a quick convergence to the ground state, especially in weakly coupled cases. Higher couplings can be handled efficiently by increasing the strength of interactions during "training".
format Preprint
id arxiv_https___arxiv_org_abs_2410_17383
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Machine Learning Approach to Trapped Many-Fermion Systems
Bedaque, Paulo F.
Kumar, Hersh
Sheng, Andy
Nuclear Theory
Disordered Systems and Neural Networks
Quantum Physics
We apply a variational Ansatz based on neural networks to the problem of spin-$1/2$ fermions in a harmonic trap interacting through a short distance potential. We showed that standard machine learning techniques lead to a quick convergence to the ground state, especially in weakly coupled cases. Higher couplings can be handled efficiently by increasing the strength of interactions during "training".
title A Machine Learning Approach to Trapped Many-Fermion Systems
topic Nuclear Theory
Disordered Systems and Neural Networks
Quantum Physics
url https://arxiv.org/abs/2410.17383