Universality class of machine learning for critical phenomena

Herein, percolation phase transitions on a two-dimensional lattice were studied using machine learning techniques. Results reveal that different phase transitions belonging to the same universality class can be identified using the same neural networks (NNs), whereas phase transitions of different universality classes require different NNs. Based on this finding, we proposed the universality class of machine learning for critical phenomena. Furthermore, we investigated and discussed the NNs of different universality classes. Our research contributes to machine learning by relating the NNs with the universality class.

Automated summary

This study investigated percolation phase transitions on a two-dimensional lattice using machine learning techniques, finding that the same neural networks can identify different phase transitions belonging to the same universality class. This research contributes to machine learning by linking neural networks with universality classes.