arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.07968hep-ph
收藏

基于机器学习的强耦合常数分布测定

Determination of the distribution of strong coupling constant with machine learning

Xiao-Yun Wang, Chen Dong, Quanjin Wang

AI总结:

本研究利用人工神经网络拟合现有数据测定强耦合常数分布,通过三项指标保障模型精度,得到不同能标下的预测值并经实验数据验证,为低能强耦合常数测定提供新途径,对量子色动力学研究有重要意义。

摘要:

在本研究中,我们采用人工神经网络(ANN)方法,通过拟合现有数据来研究并预测强耦合常数的分布。我们的方法利用了ANN学习复杂非线性关系的能力与出色的泛化性,还能对数据相关的不确定性进行系统性处理。为确保结果的可靠性,我们在训练过程中采用三项评估指标来评价模型的精度。最终,我们得到了不同能标下强耦合常数的预测值,并将其与现有实验数据进行了对比验证。我们的方法为改进低能区强耦合常数的测定提供了一种颇具前景的途径,可能对量子色动力学未来的实验与理论研究具有重要意义。

英文摘要:

In this work, we use the artificial neural network (ANN) method to study and predict the distribution of strong coupling constants by fitting the existing data. Our approach takes advantage of the ability of ANN to learn complex nonlinear relations and excellent generalization, and allows for a systematic treatment of the uncertainties associated with the data. To ensure the reliability of our results, we apply three evaluation indexes to evaluate the accuracy of model during training. Finally, we obtained the predicted values of the strong coupling constants at different energy scales, and compared and verified them with the existing experimental data. Our approach represents a promising way to improve the determination of the strong coupling constant at low energies, and could have important implications for future experimental and theoretical studies in quantum chromodynamics.

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。

↑