Electron-nucleus cross sections from transfer learning
High Energy Physics - Phenomenology
2025-08-18 v2 Machine Learning
High Energy Physics - Experiment
Nuclear Experiment
Nuclear Theory
Abstract
Transfer learning (TL) allows a deep neural network (DNN) trained on one type of data to be adapted for new problems with limited information. We propose to use the TL technique in physics. The DNN learns the details of one process, and after fine-tuning, it makes predictions for related processes. We consider the DNNs, trained on inclusive electron-carbon scattering data, and show that after fine-tuning, they accurately predict cross sections for electron interactions with nuclear targets ranging from helium-3 to iron.
Keywords
Cite
@article{arxiv.2408.09936,
title = {Electron-nucleus cross sections from transfer learning},
author = {Krzysztof M. Graczyk and Beata E. Kowal and Artur M. Ankowski and Rwik Dharmapal Banerjee and Jose Luis Bonilla and Hemant Prasad and Jan T. Sobczyk},
journal= {arXiv preprint arXiv:2408.09936},
year = {2025}
}
Comments
4 pages, 2 figures, discussion and results for helium-3 added