The neural network approach to parton distribution functions

TL;DR

This paper presents a neural network-based method for parametrizing parton distribution functions, utilizing Monte Carlo techniques and applying it to various particle physics data sets to improve the modeling of subatomic structures.

Contribution

It introduces a novel neural network approach combined with Monte Carlo methods for the parametrization of parton distributions, applicable to multiple experimental data types.

Findings

Successful application to proton structure function data

Effective modeling of hadronic tau decay spectra

Accurate parametrization of nonsinglet parton distribution

Abstract

We introduce the neural network approach to the parametrization of parton distributions. After a general introduction, we present in detail our approach to parametrize experimental data, based on a combination of Monte Carlo methods and neural networks. We apply this strategy first in three different cases: the proton structure function, hadronic tau decays and B meson decay spectra. Finally we describe the neural network approach applied to the parametrization of parton distribution functions, and present results on the nonsinglet parton distribution.