arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.09936hep-phcs.LGhep-exnucl-exnucl-th
收藏

基于迁移学习的电子-原子核散射截面

Electron-nucleus cross sections from transfer learning

Institute of Theoretical Physics, University of Wrocław(理论物理研究所,沃斯克兰大学)

Krzysztof M. Graczyk, Beata E. Kowal, Artur M. Ankowski, Rwik Dharmapal Banerjee, Jose Luis Bonilla, Hemant Prasad, Jan T. Sobczyk

AI总结:

本文提出将迁移学习引入物理研究,利用在电子-碳散射数据上训练的深度神经网络,通过微调准确预测从氦-3到铁的电子-原子核散射截面。

摘要:

迁移学习(TL)允许在一种类型数据上训练的深度神经网络(DNN)适应信息有限的新问题。我们提出在物理学中使用TL技术。DNN学习一个过程的细节,经过微调后,对相关过程进行预测。我们考虑在电子-碳散射数据上训练的DNN,并表明经过微调后,它们能够准确预测电子与从氦-3到铁的核靶相互作用的截面。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑