TY - JOUR
T1 - Rapid Classification of Quantum Sources Enabled by Machine Learning
AU - Kudyshev, Zhaxylyk A.
AU - Bogdanov, Simeon I.
AU - Isacsson, Theodor
AU - Kildishev, Alexander V.
AU - Boltasseva, Alexandra
AU - Shalaev, Vladimir M.
N1 - Z.A.K. and S.I.B. contributed equally to this work. This work was supported by the U.S. Department of Energy, Office of Basic Energy Sciences, Division of Materials Sciences and Engineering under Award DE-SC0017717 (S.I.B. and V.M.S.), DARPA/DSO Extreme Optics and Imaging (EXTREME) Program (HR00111720032, Z.A.K. and A.V.K.). This work was also supported in part by NSF EECS award 2015025.
PY - 2020/10/1
Y1 - 2020/10/1
N2 - 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.
AB - 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.
KW - machine learning
KW - quantum emitter classification
KW - single photon sources
UR - http://www.scopus.com/inward/record.url?scp=85098122952&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85098122952&partnerID=8YFLogxK
U2 - 10.1002/qute.202000067
DO - 10.1002/qute.202000067
M3 - Article
AN - SCOPUS:85098122952
SN - 2511-9044
VL - 3
JO - Advanced Quantum Technologies
JF - Advanced Quantum Technologies
IS - 10
M1 - 2000067
ER -