Machine learning techniques have been widely used in the study of strongly correlated systems in recent years. Here, we review some applications to classical and quantum many-body systems and present results from an unsupervised machine learning technique, the principal component analysis, employed to identify the finite-temperature phase transition of the three-dimensional Fermi-Hubbard model to the antiferromagnetically ordered state. We find that this linear method can capture the phase transition as well as other more complicated and nonlinear counterparts.
Ehsan Khatami. "Principal component analysis of the magnetic transition in the three-dimensional Fermi-Hubbard model" Journal of Physics: Conference Series (2019). doi:10.1088/1742-6596/1290/1/012006