基于神经网络模型的原子核基态自旋分布的随机相互作用研究  

Random Interaction Study on Angular-momentum Distribution of Nuclear Ground State with Neural Networks

作　　者：刘登 ALAM Noor A 肖越 雷杨 覃珍珍 LIU Deng;ALAM Noor A;XIAO Yue;LEI Yang;QIN Zhenzhen(School of Mathematics and Physics,Southwest University of Science and Technology,Mianyang,621010,Sichuan,China;School of Defense and Technology,Southwest University of Science and Technology,Mianyang,621010,Sichuan,China)

机构地区：[1]西南科技大学数理学院,四川绵阳621010 [2]西南科技大学国防科技学院,四川绵阳621010

出　　处：《原子核物理评论》2024年第1期385-395,共11页Nuclear Physics Review

基　　金：国家自然科学基金资助项目(12105234)。

摘　　要：利用神经网络模型学习、模拟随机两体系综(TBRE)下的原子核基态自旋分布,并对学习后的模型输入特征进行了分析。这是核物理中利用神经网络模型进行分类的典型应用。研究表明,采用本工作的单隐藏层神经网络模型,精确地描述每个随机相互作用系综内的样本仍比较困难。然而,神经网络模型却能够相对较好地描述基态自旋的统计性质,这可能是因为神经网络模型学习到了TBRE中基态自旋分布的经验规律。The neural network model is used to learn and simulate the ground state spin distribution of the nucleus under stochastic two-system ensemble(TBRE),and the input characteristics of the learned model are analyzed.This is a typical application of classification using neural network models in nuclear physics.We show that it is still difficult to accurately each the sample within random interaction ensemble using the single hidden layer neural network model in this paper.However,the NN model describes the statistical properties of the ground state spins reasonably well,probably because the NN model learned the empirical law of the ground state spin distribution in TBRE.

关 键 词：神经网络 随机两体系综 原子核基态自旋 

分 类 号：O571.53[理学—粒子物理与原子核物理]