What question did this study set out to answer?

This research focuses on evaluating nonsinglet distribution functions using advanced computational techniques.

February 7, 2026The European Physical Journal A0 citations

Nonsinglet distribution functions using the neural network and genetic algorithm

EAE. AstarakiRazi University GBG. R. BorounRazi University

Key Points

This research focuses on evaluating nonsinglet distribution functions using advanced computational techniques.
Utilized neural networks for function approximation
Employed genetic algorithms for optimization
Analyzed results against existing parameterizations
Nonsinglet distribution functions align well with CT18, MMHT14, MSHT20, and NNPDF4.0
Improvements in approximation accuracy noted using neural networks and genetic algorithms

Abstract

We examine the nonsinglet distribution functions \ ( (xuᵥ, xdᵥ) \) using neural networks and genetic algorithms at the initial scale \ (Q²₀\). Evaluation of the distribution functions by the DGLAP equation can illuminate the nonsinglet distributions in a wide range of x and \ (Q²\) at the leading-order up to higher-order approximations. These results based on the neural networks and genetic algorithm are in good agreement with the CT18, MMHT14, MSHT20 and NNPDF4. 0 parameterization groups.

Ask AI

Helpful

Bookmark

View Full Paper