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 2007.01037physics.comp-phcond-mat.dis-nncond-mat.stat-mech
收藏

神经网络统计力学

Neural Network Statistical Mechanics

Lingxiao Wang, Yin Jiang, Kai Zhou

摘要:

我们提出了一个通用框架,用于使用深度神经网络从原始配置中提取微观相互作用。该方法用神经网络代替建模的哈密顿量,在神经网络中相互作用被编码。它可以用从头计算或实验收集的数据进行训练。训练良好的神经网络给出了一个准确的估计的可能性分布的配置在固定的外部参数。从经典统计力学的先验知识出发,可以自发地外推到检测相结构。我们将该方法应用于2D自旋系统,在固定温度下训练,并再现相结构。将组态标度到点阵上,可以很自然地反映出相互作用随自由度的变化,这一点可以很自然地应用到实验测量中。我们的方法与自回归神经网络的真实配置和微观动力学之间的差距桥梁。

英文摘要:

We propose a general framework to extract microscopic interactions from raw configurations with deep neural networks. The approach replaces the modeling Hamiltonian by the neural networks, in which the interaction is encoded. It can be trained with data collected from Ab initio computations or experiments. The well-trained neural networks give an accurate estimation of the possibility distribution of the configurations at fixed external parameters. It can be spontaneously extrapolated to detect the phase structures since classical statistical mechanics as prior knowledge here. We apply the approach to a 2D spin system, training at a fixed temperature, and reproducing the phase structure. Scaling the configuration on lattice exhibits the interaction changes with the degree of freedom, which can be naturally applied to the experimental measurements. Our approach bridges the gap between the real configurations and the microscopic dynamics with an autoregressive neural network.

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。

↑