Self-Organizing Maps and Parton Distributions Functions

TL;DR

This paper introduces a novel neural network-based method using Self-Organizing Maps to extract parton distribution functions from high energy experimental data, improving analysis of generalized distributions.

Contribution

The paper presents a new approach employing Self-Organizing Maps for extracting parton distribution functions, offering advantages for analyzing generalized distributions from experimental data.

Findings

Successful initial extraction of parton distribution functions from deep inelastic scattering data.

Demonstrated the method's effectiveness for analyzing generalized parton distributions.

Provided quantitative results supporting the new approach.

Abstract

We present a new method to extract parton distribution functions from high energy experimental data based on a specific type of neural networks, the Self-Organizing Maps. We illustrate the features of our new procedure that are particularly useful for an anaysis directed at extracting generalized parton distributions from data. We show quantitative results of our initial analysis of the parton distribution functions from inclusive deep inelastic scattering.