Reliable single-photon sources are vital for quantum communication and computing. We demonstrate a deep-learning method that distinguishes true single-photon sources from pseudo-thermal light from minimal temporal data, rather than statistical photon count distributions obtained over long acquisition periods. Our model performs effectively at over 98% accuracy in low-intensity and mixed-state conditions for efficient photon-source identification.
Reliable single-photon sources are vital for quantum communication and computing. We demonstrate a deep-learning method that distinguishes true single-photon sources from pseudo-thermal light from minimal temporal data, rather than statistical photon count distributions obtained over long acquisition periods. Our model performs effectively at over 98% accuracy in low-intensity and mixed-state conditions for efficient photon-source identification.
The identification of light sources represents a task of utmost importance for the development of multiple photonic technologies. Over the last decades, the identification of light sources as diverse as sunlight, laser radiation, and molecule fluorescence has relied on the collection of photon statistics or the implementation of quantum state tomography. In general, this task requires an extensive number of measurements to unveil the characteristic statistical fluctuations and correlation properties of light, particularly in the low-photon flux regime. In this article, we exploit the self-learning features of artificial neural networks and the naive Bayes classifier to dramatically reduce the number of measurements required to discriminate thermal light from coherent light at the single-photon level. We demonstrate robust light identification with tens of measurements at mean photon numbers below one. In terms of accuracy and number of measurements, the methods described here dramatically outperform conventional schemes for characterization of light sources. Our work has important implications for multiple photonic technologies such as light detection and ranging, and microscopy.
Identification of a suitable source of single photons via second-order autocorrelation function measurement within an array of thousand possible candidates is a routine, key step of any practical realization in quantum optics. Within this work, we have shown that machine learning algorithms enable high precision classification between “single” and “not single” quantum emitters based on sparse autocorrelation data measurement and require < 1 s acquisition time, while conventional methods demand > 1 min. Machine learning assisted classification, done on a sparse 1-s dataset, provides ~85% accuracy of “single”/“not single” emitter identification versus only 57% of the conventional Levenberg-Marquardt approach.
Characterization of the photon statistics of an optical field is central to identifying light sources in various quantum-enabled technologies, from super-resolved quantum imaging to precise quantum sensing and spectroscopy. In practice, however, estimating photon-correlation functions with sufficient accuracy requires long acquisition times and computationally intensive statistical estimators, severely limiting real-time operation and the study of rapidly varying or weak sources. Here, we show that learned inference based on artificial neural networks enables rapid estimation of second-order coherence directly from photon-number-resolved measurements, outperforming the precision of conventional statistical methods with processing times three orders of magnitude shorter. Our approach is source-agnostic and remains accurate in few-photon illumination regimes where the statistics of coherent, partially coherent, thermal, and super-thermal light become nearly indistinguishable. We experimentally validate the method across more than 4000 distinct classical light sources, demonstrating equal or improved precision with drastically reduced data and computational requirements. These results establish machine-learning-enabled photon-statistics inference as a new operational route to rapid optical-coherence diagnostics, enabling real-time monitoring of classical light sources in regimes previously inaccessible to conventional estimators.
Quantum correlation, as an intrinsic property of quantum mechanics, has been widely employed to test the fundamental physical principles and explore the quantum-enhanced technologies. However, such correlation would be drowned and even destroyed in the conditions of high levels of loss and noise, which drops into the classical realm and renders quantum advantage ineffective. Especially in low light conditions, conventional linear classifiers are unable to extract and distinguish quantum and classical correlations with high accuracy. Here we experimentally demonstrate the classification of quantum correlation using deep learning to meet the challenge in the quantum imaging scheme. We design the convolutional neural network to learn and classify the correlated photons efficiently with only 0.1 signal photons per pixel. We show that decreasing signal intensity further weakens the correlation and makes an accurate linear classification impossible, while the deep learning method has a strong robustness of such task with the accuracy of 99.99%. These results open up a new perspective to optimize the quantum correlation in low light conditions, representing a step towards diverse applications in quantum-enhanced measurement scenarios, such as super-resolution microscope, quantum illumination, etc.
The technologies utilizing quantum states of light have been in the spotlight for the last two decades. In this regard, quantum metrology, quantum imaging, quantum-optical communication are some of the important applications that exploit fascinating quantum properties like quantum superposition, quantum correlations, and nonclassical photon statistics. However, the state-of-art technologies operating at the single-photon level are not robust enough to truly realize a reliable quantum-photonic technology. In Chapter 1, I present a historical account of photon-based technologies. Furthermore, I discuss recent efforts and encouraging developments in the field of quantum-photonic technologies, and major challenges for the experimental realization of reliable quantum technologies utilizing photons, setting up a stage for unveiling our smart methodologies to cope with them. Similarly, in Chapter 2, I review the fundamental concepts such as states of light, spatial modes of light, and machine learning. In Chapter 3 of this dissertation, I present a theoretical work on a nonlinear quantum metrology scheme, showing a sub-shot-noise limited phase estimation using the displaced-squeezed light and on/off detection. Furthermore, I discuss a camera-based squeezed-light detection technique that can be a smart and time-efficient alternative to conventional balanced-homodyne detection. In Chapter 4, I discuss our efforts to incorporate artificial intelligence in a quest to improve the efficiency of discriminating thermal light sources from coherent light sources. The conventional identification technique requires a large number of measurements. We utilize artificial neural networks to dramatically reduce the number of measurements required to distinguish thermal light and coherent light. In Chapter 5, I present a communication protocol that utilizes the spatial modes of light. Despite being valuable resources for a wide variety of quantum technologies, spatial modes of light are extremely vulnerable to random phase fluctuations. The conventional techniques to cope with these challenges are relatively inefficient. We utilize convolutional neural networks to perform the spatial mode correction of single photons, resulting in a near-unity fidelity of correction. I wrap up my dissertation in Chapter 6 by summarizing the historical context of quantum technologies, challenging problems facing state-of-art quantum technologies, and the importance of our efforts to introduce artificial intelligence in photonic technologies.
Abstract Advancements in optical quantum technologies have been enabled by the generation, manipulation, and characterization of light, with identification based on its photon statistics. However, characterizing light and its sources through single photon measurements requires efficient detectors and longer measurement times to obtain high‐quality photon statistics. Here, a deep learning‐based variational autoencoder (VAE) method is introduced for classifying single photon added coherent state (SPACS), single photon added thermal state (SPATS), and mixed states between coherent and SPACS as well as between thermal and SPATS of light. The semi‐supervised learning‐based VAE efficiently maps the photon statistics features of light to a lower dimension, enabling quasi‐instantaneous classification with low average photon counts. The proposed VAE method is robust and maintains classification accuracy in the presence of losses inherent in an experiment, such as finite collection efficiency, non‐unity quantum efficiency, finite number of detectors, etc. Additionally, leveraging the transfer learning capabilities of VAE enables successful classification of data of any quality using a single trained model. It is envisioned that such a deep learning methodology will enable better classification of quantum light and light sources even in poor detection.