摘要
A modified deep convolutional generative adversarial network(M-DCGAN)frame is proposed to study the N-dimensional(ND)topological quantities in lattice QCD based on Monte Carlo(MC)simulations.We construct a new scaling structure including fully connected layers to support the generation of high-quality high-dimensional images for the M-DCGAN.Our results suggest that the M-DCGAN scheme of machine learning will help to more efficiently calculate the 1D distribution of topological charge and the 4D topological charge density compared with MC simulation alone.
作者
高璘
应和平
张剑波
Lin Gao;Heping Ying;Jianbo Zhang(School of Physics,Zhejiang University,Hangzhou 310027,China)
