期刊
PHYSICS LETTERS B
卷 834, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.physletb.2022.137394
关键词
Multi-task learning; Nuclear masses; Separation energies; Gradient kernel ridge regression
资金
- National Key R&D Program of China [2018YFA0404400, 2017YFE0116700]
- National Natural Science Foundation of China [11875075, 11935003, 11975031, 12141501, 12070131001]
- China Postdoctoral Science Foundation [2021M700256]
- High performance Computing Platform of Peking University
A multi-task learning framework, gradient kernel ridge regression, is developed for predicting nuclear masses and separation energies by introducing gradient kernel functions to the kernel ridge regression approach. The framework is trained using the WS4 mass model and improves the accuracy of theoretical predictions by considering the deviations between experimental and theoretical values. Significant improvements are achieved in both interpolation and extrapolation predictions for nuclear masses and separation energies.
A multi-task learning (MTL) framework, called gradient kernel ridge regression, for nuclear masses and separation energies is developed by introducing gradient kernel functions to the kernel ridge regression (KRR) approach. By taking the WS4 mass model as an example, the gradient KRR network is trained with the mass model residuals, i.e., deviations between experimental and theoretical values of masses and one-nucleon separation energies, to improve the accuracy of theoretical predictions. Significant improvements are achieved by the gradient KRR approach in both the interpolation and the extrapolation predictions of nuclear masses and separation energies. This demonstrates the advantage of the present MTL framework that integrates the information of nuclear masses and separation energies and improves the predictions for both of them. (C) 2022 The Author(s). Published by Elsevier B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据