English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automated tuning of gate-defined quantum dots is a requirement for largescale semiconductor based qubit initialisation. An essential step of thesetuning procedures is charge state detection based on charge stability diagrams.Using supervised machine learning to perform this task requires a large datasetfor models to train on. In order to avoid hand labelling experimental data,synthetic data has been explored as an alternative. While providing asignificant increase in the size of the training dataset compared to usingexperimental data, using synthetic data means that classifiers are trained ondata sourced from a different distribution than the experimental data that ispart of the tuning process. Here we evaluate the prediction accuracy of a rangeof machine learning models trained on simulated and experimental data and theirability to generalise to experimental charge stability diagrams in twodimensional electron gas and nanowire devices. We find that classifiers performbest on either purely experimental or a combination of synthetic andexperimental training data, and that adding common experimental noisesignatures to the synthetic data does not dramatically improve theclassification accuracy. These results suggest that experimental training dataas well as realistic quantum dot simulations and noise models are essential incharge state detection using supervised machine learning.

Evaluation of synthetic and experimental training data in supervised machine learning applied to charge state detection of quantum dots