Electron-Nucleus Cross Sections from Transfer Learning
Open Access
- 1 August 2025
- journal article
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 135 (5) , 052502
Abstract
Transfer learning 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 transfer learning 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
All Related Versions
Funding Information
- Narodowe Centrum Nauki (UMO-2021/41/B/ST2/ 02778)
- Uniwersytet Wrocławski
This publication has 25 references indexed in Scilit:
- Empirical fits to inclusive electron-carbon scattering data obtained by deep-learning methodsPhysical Review C, 2024
- Electron scattering and neutrino physicsJournal of Physics G: Nuclear and Particle Physics, 2023
- Volume I. Introduction to DUNEJournal of Instrumentation, 2020
- Physics potential of a long-baseline neutrino oscillation experiment using a J-PARC neutrino beam and Hyper-KamiokandeProgress of Theoretical and Experimental Physics, 2015
- Quasielastic electron scattering fromCaPhysical Review C, 1997
- Quasi-elastic and inelastic inclusive electron scattering from an oxygen jet targetNuclear Physics A, 1996
- Inclusive electron-nucleus scattering at high momentum transferPhysical Review C, 1993
- Measurements of ν and R=/ from inelastic electron-aluminum scattering near x=1Physical Review C, 1992
- Electromagnetic excitation of the delta resonance in nucleiPhysical Review C, 1987
- Transverse and longitudinal response functions in deep inelastic electron scattering from 3HePhysics Letters B, 1985