Neural Network Generalized Parton Distributions (NNGPD)

TL;DR

This paper introduces a deep learning framework to extract generalized parton distributions (GPDs) from experimental and lattice QCD data, advancing proton structure analysis.

Contribution

It presents a novel deep learning-assisted method for extracting GPDs from diverse data sources, combining experimental results with lattice QCD calculations.

Findings

Successfully applied deep learning to extract GPDs from data

Demonstrated consistency between experimental and lattice QCD GPDs

Enhanced understanding of proton structure through this method

Abstract

Generalized parton distributions (GPDs) serve as indispensable tools for the exploration of proton structure. In this study, we offer a deep learning-assisted framework for the extraction of GPDs from experimental data and the results of ab-initio lattice quantum chromodynamics (LQCD).