Applying machine learning methods to prediction problems of lattice observables - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Applying machine learning methods to prediction problems of lattice observables

Abstract

We discuss the prediction of critical behavior of lattice observables in SU(2) and SU(3) gauge theories. We show that feed-forward neural network, trained on the lattice configurations of gauge fields as input data, finds correlations with the target observable, which is also true in the critical region where the neural network has not been trained. We have verified that the neural network constructs a gauge-invariant function and this property does not change over the entire range of the parameter space.
Fichier principal
Vignette du fichier
Proceedings_Hard_Problems_of_Hadron_Physics.pdf (1.17 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03472367 , version 1 (09-12-2021)

Identifiers

Cite

Maxim N. Chernodub, N V Gerasimeniuk, V A Goy, D L Boyda, S D Liubimov, et al.. Applying machine learning methods to prediction problems of lattice observables. XXXIII International (ONLINE) Workshop on High Energy Physics “Hard Problems of Hadron Physics: Non-Perturbative QCD & Related Quests”, Nov 2021, Protvino, Russia. pp.10005, ⟨10.1051/epjconf/202225810005⟩. ⟨hal-03472367⟩
43 View
94 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More