Neural Network Parameterizations of Electromagnetic Nucleon Form Factors

TL;DR

This paper employs Bayesian neural networks to model electromagnetic nucleon form factors, providing unbiased, model-independent parametrizations with quantified uncertainties, and selecting optimal models based on evidence measures.

Contribution

It introduces a Bayesian neural network approach for form-factor parametrization, enabling unbiased, data-driven models with uncertainty estimates and model selection via evidence.

Findings

Neural networks effectively model nucleon form factors.

Bayesian framework quantifies uncertainties in parametrizations.

Evidence-based model selection identifies optimal neural network configurations.

Abstract

The electromagnetic nucleon form-factors data are studied with artificial feed forward neural networks. As a result the unbiased model-independent form-factor parametrizations are evaluated together with uncertainties. The Bayesian approach for the neural networks is adapted for chi2 error-like function and applied to the data analysis. The sequence of the feed forward neural networks with one hidden layer of units is considered. The given neural network represents a particular form-factor parametrization. The so-called evidence (the measure of how much the data favor given statistical model) is computed with the Bayesian framework and it is used to determine the best form factor parametrization.