Exploring Nucleon Structure with the Self-Organizing Maps Algorithm

TL;DR

This paper explores using Self-Organizing Maps, a neural network type, to extract parton distribution functions from hard scattering data, offering a novel approach in nucleon structure analysis.

Contribution

It introduces the application of Self-Organizing Maps to analyze nucleon structure, providing an alternative method to traditional neural network techniques.

Findings

Successful extraction of parton distribution functions using SOMs

Demonstrates SOMs' effectiveness in analyzing hard scattering data

Provides a new tool for nucleon structure studies

Abstract

We discuss the application of an alternative type of neural network, the Self-Organizing Map to extract parton distribution functions from various hard scattering processes.