Rapid Classification of Quantum Sources Enabled by Machine Learning

• Published in: Advanced quantum technologies (Online) 2020-10, Vol.3 (10), p.n/a
• Main Authors: Kudyshev, Zhaxylyk A., Bogdanov, Simeon I., Isacsson, Theodor, Kildishev, Alexander V., Boltasseva, Alexandra, Shalaev, Vladimir M.
• Format: Article
• Language: English
• Subjects: Autocorrelation; Classification accuracy; Learning systems; machine learning; Nanophotonic devices; Nanoscale building blocks; Optical characterization; Particle beams; Photonic devices; quantum emitter classification; Quantum emitters; Quantum photonics; Single photon emitters; single photon sources; Supervised learning; Supervised machine learning
• ISSN: 2511-9044; 2511-9044
• DOI: 10.1002/qute.202000067

Deterministic nanoassembly may enable unique integrated on‐chip quantum photonic devices. Such integration requires a careful large‐scale selection of nanoscale building blocks such as solid‐state single‐photon emitters by means of optical characterization. Second‐order autocorrelation is a cornerstone measurement that is particularly time‐consuming to realize on a large scale. Supervised machine learning‐based classification of quantum emitters as “single” or “not‐single” is implemented based on their sparse autocorrelation data. The method yields a classification accuracy of 95% within an integration time of less than a second, realizing roughly a 100‐fold speedup compared to the conventional Levenberg–Marquardt fitting approach. It is anticipated that machine learning‐based classification will provide a unique route to enable rapid and scalable assembly of quantum nanophotonic devices. Supervised machine learning‐based classification of quantum emitters as “single” or “not‐single” is implemented based on their sparse autocorrelation data. The method yields a classification accuracy of 95% within an integration time of less than a second, realizing roughly a 100‐fold speedup compared to the conventional Levenberg–Marquardt fitting approach.