Classical and quantum machine learning applications in spintronics

TL;DR

This paper explores how classical and quantum machine learning techniques can predict complex quantum transport and spin responses in spintronic devices, enabling more accurate modeling of large-scale quantum systems.

Contribution

It introduces machine learning methods for predicting quantum transport properties, demonstrating improved accuracy and scalability over traditional approaches in spintronics applications.

Findings

Machine learning accurately predicts conductance and spin responses.

Classification approach outperforms linear response predictions.

Quantum machine learning handles large configuration spaces effectively.

Abstract

In this article we demonstrate the applications of classical and quantum machine learning in quantum transport and spintronics. With the help of a two-terminal device with magnetic impurity we show how machine learning algorithms can predict the highly non-linear nature of conductance as well as the non-equilibrium spin response function for any random magnetic configuration. By mapping this quantum mechanical problem onto a classification problem, we are able to obtain much higher accuracy beyond the linear response regime compared to the prediction obtained with conventional regression methods. We finally describe the applicability of quantum machine learning which has the capability to handle a significantly large configuration space. Our approach is applicable for solid state devices as well as for molecular systems. These outcomes are crucial in predicting the behavior of large-scale systems where a quantum mechanical calculation is computationally challenging and therefore would play a crucial role in designing nano devices.