Rapid classification of quantum sources enabled by machine learning

Abstract

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 the means of optical characterization. Second-order autocorrelation is a cornerstone measurement that is particularly time-consuming to realize on a large scale. We have implemented supervised machine learning-based classification of quantum emitters as "single" or "not-single" based on their sparse autocorrelation data. Our method yields a classification accuracy of over 90% within an integration time of less than a second, realizing roughly a hundredfold speedup compared to the conventional, Levenberg-Marquardt approach. We anticipate that machine learning-based classification will provide a unique route to enable rapid and scalable assembly of quantum nanophotonic devices and can be directly extended to other quantum optical measurements.

arXiv commentAdv. Quantum Technol. 2020

References in corpus (28)

• Scikit-learn: Machine Learning in Python
• Deep Learning with Coherent Nanophotonic Circuits
• Quantum Convolutional Neural Networks
• On-Demand Single Photons with High Extraction Efficiency and Near-Unity Indistinguishability from a Resonantly Driven Quantum Dot in a Micropillar
• Large-scale quantum-emitter arrays in atomically thin semiconductors
• Photon antibunching in the fluorescence of individual color centers in diamond
• Boson sampling with 20 input photons in 60-mode interferometers at $10^{14}$ state spaces
• Training of photonic neural networks through in situ backpropagation
• Large-scale integration of near-indistinguishable artificial atoms in hybrid photonic circuits
• Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks
• Active learning machine learns to create new quantum experiments
• Hybrid integration methods for on-chip quantum photonics
• Super-resolution enhancement by quantum image scanning microscopy
• Experimental Quantum Hamiltonian Learning
• Three megahertz photon collection rate from an NV center with millisecond spin coherence
• Scalable Focused Ion Beam Creation of Nearly Lifetime-Limited Single Quantum Emitters in Diamond Nanostructures
• Hybrid integration of solid-state quantum emitters on a silicon photonic chip
• Hamiltonian Learning and Certification Using Quantum Resources
• Machine Learning for Precise Quantum Measurement
• Experimental neural network enhanced quantum tomography
• Fabrication of all diamond scanning probes for nanoscale magnetometry
• Matrix optimization on universal unitary photonic devices
• Beating Abbe diffraction limit in confocal microscopy via non-classical photon statistics
• Integrating Neural Networks with a Quantum Simulator for State Reconstruction
• Single-photon decision maker
• Efficient signal processing for time-resolved fluorescence detection of nitrogen-vacancy spins in diamond
• Reconstruction of a Photonic Qubit State with Reinforcement Learning
• Dynamical modeling of pulsed two-photon interference

Cited by in corpus (8)

• Deep learning in nano-photonics: inverse design and beyond
• Tunable nanophotonics enabled by chalcogenide phase-change materials
• Accelerating ultrafast spectroscopy with compressive sensing
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• Heterogeneous integration of solid state quantum systems with a foundry photonics platform
• Optimized higher-order photon state classification by machine learning
• Efficient Analysis of Photoluminescence Images for the Classification of Single-Photon Emitters
• Quantifying Quantum Steering with Limited Resources: A Semi-supervised Machine Learning Approach