论文标题
神经网络统计力学
Neural Network Statistical Mechanics
论文作者
论文摘要
我们提出了一个通用框架，以从具有深神经网络的原始配置中提取微观相互作用。该方法用神经网络代替了建模哈密顿量，其中相互作用被编码。可以通过从头算计算或实验收集的数据对其进行培训。训练有素的神经网络对固定外部参数下配置的可能性分布进行了准确的估计。可以自发推断以检测相结构，因为在这里经典的统计力学作为先验知识。我们将方法应用于2D自旋系统，在固定温度下训练并重现相结构。在晶格上缩放构型表现出与自由度的相互作用变化，可以自然地应用于实验测量。我们的方法弥合了实际配置与微观动力学之间的差距，并具有自回归神经网络。
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.
