A study of topological quantities of lattice QCD by a modified DCGAN frame

Abstract

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 the 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 show that the M-DCGAN scheme of the Machine learning should be helpful for us to calculate efficiently the 1D distribution of topological charge and the 4D topological charge density compared with the case by the MC simulation alone.