Machine learning non-Hermitian topological phases

TL;DR

This paper demonstrates that machine learning, specifically neural networks, can accurately identify and predict non-Hermitian topological phases in both one and three dimensions, even with disorder.

Contribution

It introduces a machine learning approach to classify non-Hermitian topological phases based on their winding number, showing high accuracy and robustness.

Findings

Neural networks achieve over 99.9% accuracy in 1D models.

Convolutional neural networks effectively classify 3D topological phases.

Method is robust to disorder in the models.

Abstract

Non-Hermitian topological phases have gained widespread interest due to their unconventional properties, which have no Hermitian counterparts. In this work, we propose to use machine learning to identify and predict non-Hermitian topological phases, based on their winding number. We consider two examples -- non-Hermitian Su-Schrieffer-Heeger model and its generalized version in one dimension and non-Hermitian nodal line semimetal in three dimensions -- to demonstrate the use of neural networks to accurately characterize the topological phases. We show that for the one dimensional model, a fully connected neural network gives an accuracy greater than 99.9\%, and is robust to the introduction of disorder. For the three dimensional model, we find that a convolutional neural network accurately predicts the different topological phases.