Self-Orgazing Maps Parametrization of Parton Distribution Functions

TL;DR

This paper introduces a novel neural network-based method using Self-Organizing Maps to extract parton distribution functions, providing initial quantitative results in the unpolarized case.

Contribution

It presents a new approach employing Self-Organizing Maps for parametrizing parton distribution functions, applicable to both polarized and unpolarized cases.

Findings

Initial results for unpolarized PDFs at Next to Leading Order

Demonstrates feasibility of neural network approach in this context

Provides a foundation for further detailed analysis

Abstract

We describe a new method to extract parton distribution functions both in the unpolarized and the polarized case, based on a type of neural networks, the Self-Organizing Maps. Initial quantitative results of our Next to Leading Order analysis are presented for the unpolarized case.