Machine learning is becoming widely used in analyzing the thermodynamics of many-body condensed matter systems. Restricted Boltzmann machine (RBM) aided Monte Carlo simulations have sparked interest, as they manage to speed up classical Monte Carlo simulations. In the poster/talk, based on my paper (Phys. Rev. B 102, 195148), I will explain how we used the convolutional restricted Boltzmann machine (CRBM) method to reduce the number of parameters to be learned drastically by taking advantage of translation invariance. Furthermore, I will show that it is possible to train the CRBM at smaller lattice sizes, and apply it to larger lattice sizes. To demonstrate the efficiency of CRBM, I show the application to the Ising and honeycomb Kitaev models.

Download the slides for this talk.Download ( PDF, 1319.7 MB)