Download | - View final version: Robust quantum dots charge autotuning using neural network uncertainty (PDF, 2.2 MiB)
|
---|
DOI | Resolve DOI: https://doi.org/10.1088/2632-2153/ad88d5 |
---|
Author | Search for: Yon, VictorORCID identifier: https://orcid.org/0000-0003-4517-5042; Search for: Galaup, BastienORCID identifier: https://orcid.org/0009-0005-0384-1109; Search for: Rohrbacher, ClaudeORCID identifier: https://orcid.org/0009-0003-5789-3807; Search for: Rivard, Joffrey; Search for: Godfrin, ClémentORCID identifier: https://orcid.org/0000-0002-5244-3474; Search for: Li, RuoyuORCID identifier: https://orcid.org/0000-0002-2145-7590; Search for: Kubicek, Stefan; Search for: De Greve, KristiaanORCID identifier: https://orcid.org/0000-0002-1314-9715; Search for: Gaudreau, Louis1ORCID identifier: https://orcid.org/0000-0002-1929-2715; Search for: Dupont-Ferrier, Eva; Search for: Beilliard, YannORCID identifier: https://orcid.org/0000-0003-0311-8840; Search for: Melko, Roger GORCID identifier: https://orcid.org/0000-0002-5505-8176; Search for: Drouin, DominiqueORCID identifier: https://orcid.org/0000-0003-2156-967X |
---|
Affiliation | - National Research Council of Canada. Quantum and Nanotechnologies
|
---|
Funder | Search for: Fonds de Recherche du Québec - Nature et Technologies; Search for: National Science Engineering Research Council of Canada |
---|
Format | Text, Article |
---|
Subject | artificial neural network; Bayesian nerual network; quantum dot; charge autotuning; uncertainty estimation |
---|
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 network uncertainty estimations. Tested across three distinct offline experimental datasets representing different single-quantum-dot technologies, this approach achieves a tuning success rate of over 99% 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. |
---|
Publication date | 2024-11-07 |
---|
Publisher | IOP Publishing |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | aee92f00-a3f7-4a2d-814e-4a47153aaa1b |
---|
Record created | 2025-04-02 |
---|
Record modified | 2025-04-02 |
---|