Machine learning and its application to lattice Monte Carlo simulations

Recent development of machine learning (ML), especially deep learning is remarkable. It has been applied to image recognition, image generation and so on with very good precision. From a mathematical point of view, images are just real matrices, so it would be a natural idea to replace this matrices with the configurations of the physical system created by numerical simulation and see what happens. In this talk, I will review basics on ML and recent attempts to improve Markov Chain Monte Carlo simulations including our work on reducing autocorrelation of Hamiltonian Monte Carlo (HMC) algorithm.