SciPost logo

Applying machine learning methods to prediction problems of lattice observables

N. V. Gerasimeniuk, M. N. Chernodub, V. A. Goy, D. L. Boyda, S. D. Liubimov, A. V. Molochkov

SciPost Phys. Proc. 6, 020 (2022) · published 31 May 2022

Proceedings event

XXXIII International Workshop on High Energy Physics

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.


Authors / Affiliations: mappings to Contributors and Organizations

See all Organizations.
Funders for the research work leading to this publication