Robust quantum dots charge autotuning using neural network uncertainty

TL;DR

This paper introduces a neural network-based method for automating charge tuning in semiconductor spin qubits, significantly reducing human effort and improving robustness by leveraging uncertainty estimations, with high success rates across diverse datasets.

Contribution

The study develops a novel machine learning procedure that uses neural network uncertainty to guide charge tuning in quantum dots, enabling scalable and reliable automation.

Findings

Achieves over 99% success rate in optimal conditions

Utilizes neural network uncertainty to enhance robustness

Effective across multiple quantum dot technologies

Abstract

This study presents a machine-learning-based procedure to automate the charge tuning of semiconductor spin qubits with minimal human intervention, addressing one of the significant challenges in scaling up quantum dot technologies. This method exploits artificial neural networks to identify noisy transition lines in stability diagrams, guiding a robust exploration strategy leveraging neural networks' uncertainty estimations. Tested across three distinct offline experimental datasets representing different single quantum dot technologies, the approach achieves over 99% tuning success rate in optimal cases, where more than 10% of the success is directly attributable to uncertainty exploitation. The challenging constraints of small training sets containing high diagram-to-diagram variability allowed us to evaluate the capabilities and limits of the proposed procedure.