Study of the mass of pseudoscalar glueball with a deep neural network

TL;DR

This paper employs a specially designed deep neural network to improve the accuracy and stability of pseudoscalar glueball mass estimation in lattice QCD, outperforming traditional methods.

Contribution

Introduces a new DNN architecture tailored for lattice QCD data to enhance mass estimation accuracy and stability.

Findings

DNN yields more precise mass estimates than least squares.

The new network improves stability of the mass determination.

Results demonstrate the effectiveness of deep learning in lattice QCD analysis.

Abstract

A deep neural network (DNN) is utilized to study the mass of the pseudoscalar glueball in lattice QCD based on Monte Carlo simulations. To obtain an accurate and stable mass value, I constructed a new network. The results show that this DNN provides a more precise and stable mass estimate compared to the traditional least squares method.