Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

APL Machine Learning

Experimental realization of a quantum classification: Bell state measurement via machine learning

Qingyuan Wu, Zhe Meng, Xiao-Xiao Chen, Jian Li, Jia-Zhi Yang, An‐Ning Zhang

Published Sep 1, 2023• 2 citations
Publisher

Abstract

The Bell state is a crucial resource for the realization of quantum information tasks, and when combined with orbital angular momentum (OAM), it enables a high-dimensional Hilbert space, which is essential for high-capacity quantum communication. In this study, we demonstrate the recognition of OAM Bell states using interference patterns generated by a classical light source and a single-photon source from a Sagnac interferometer-based OAM Bell state evolution device. The interference patterns exhibit a one-to-one correspondence with the input Bell states, providing conclusive evidence for the full recognition of OAM Bell states. Furthermore, we introduce machine learning to the field of Bell state recognition by proposing a neural network model capable of accurately recognizing higher order single-photon OAM Bell states, even in the undersampling case. In particular, the model’s training set includes interference patterns of OAM Bell states generated by classical light sources, yet it is able to recognize single-photon OAM Bell states with high accuracy, without relying on quantum resources during training. Our innovative application of neural networks to the recognition of single-photon OAM Bell states not only circumvents the resource consumption and experimental difficulties associated with quantum light sources but also facilitates the study of OAM-based quantum information.

DOI
10.1063/5.0149414

Related papers

Imaging of Single-Photon Orbital-Angular-Momentum Bell States

Xiao-Xiao Chen, Qingyuan Wu, Zhe Meng +4 more

Bell states are the most fundamental resource in realizing quantum information tasks and have a very unique position in quantum mechanics. Utilizing orbital angular momentum (OAM) to encode single-photon Bell states enables the realization of high-dimensional Hilbert space, which is crucial for the field of quantum information. In this paper, we design a single-photon OAM Bell-state evolution device based on the Sagnac interferometer, which can make one-to-one correspondence between the input Bell states and the output states. Moreover, we also develop a single-photon single-pixel imaging (SPI) technique, which improves spatial resolution and decreases acquisition time in the meantime, to capture interference images of output states. The results show that single-photon OAM Bell states can be fully recognized by comparing the differences of interference images. We innovatively utilize the SPI technique for single-photon OAM Bell-state recognition. This indicates that the SPI technique effectively promotes the study of quantum information based on OAM, while the quantum information based on OAM provides a clear application scenario for the SPI technique.

Physical Review Applied•Nov 17, 2022•10 citations

Deep learning as a tool to distinguish between high orbital angular momentum optical modes

Erin M. Knutson, Sanjaya Lohani, Onur Danaci +2 more

The generation of light containing large degrees of orbital angular momentum (OAM) has recently been demon- strated in both the classical and quantum regimes. Since there is no fundamental limit to how many quanta of OAM a single photon can carry, optical states with an arbitrarily high difference in this quantum number may, in principle, be entangled. This opens the door to investigations into high-dimensional entanglement shared between states in superpositions of nonzero OAM. Additionally, making use of non-zero OAM states can allow for a dramatic increase in the amount of information carried by a single photon, thus increasing the information capacity of a communication channel. In practice, however, it is difficult to differentiate between states with high OAM numbers with high precision. Here we investigate the ability of deep neural networks to differentiate between states that contain large values of OAM. We show that such networks may be used to differentiate be- tween nearby OAM states that contain realistic amounts of noise, with OAM values of up to 100. Additionally, we examine how the classification accuracy scales with the signal-to-noise ratio of images that are used to train the network, as well as those being tested. Finally, we demonstrate the simultaneous classification of < 100 OAM states with greater than 70 % accuracy. We intend to verify our system with experimentally-produced classi- cal OAM states, as well as investigate possibilities that would allow this technique to work in the few-photon quantum regime.

Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE•Sep 14, 2016•65 citations

Complete measurement and multiplexing of orbital angular momentum Bell states

Ling‐Jun Kong, Yongnan Li, Rui Liu +10 more

Orbital angular momentum (OAM) entanglement states have great potential in enhancing the information capacity in quantum communications. To make full use of the OAM degree of freedom, the measurement and distinction of OAM Bell states become a key step that needs to be accomplished. However, there is still no solution to achieve complete distinction of OAM Bell states at the single-photon level. Here we demonstrate the complete OAM Bell-state measurement without auxiliary photons by using linear optics. Furthermore, we propose a quantum communication network via OAM Bell-state multiplexing, perform a proof-of-principle experiment in the first- and second-order OAM subspaces for two users, and achieve average success probabilities of obtaining information of 91.6% for User-I and 89.1% for User-II. In principle, our scheme allows more users to be added by using high-order OAM Bell states. Our research extends the manipulation method for high-dimensional quantum states and paves the way for the application of OAM multiplexing in quantum communications.

Physical Review A•Aug 14, 2019•18 citations

Machine learning based recognition of Orbital Angular Momentum modes for Satellite Communication

Prithviraj Bhavikatti, Ashlesh H Upadhyaya, J. Manikandan

Orbital angular momentum (OAM) of light has enabled quantum encoding in higher dimensional Hilbert spaces, opening up new opportunities for high capacity satellite-to-ground quantum communications. In this paper, machine learning based recognition of OAM modes for satellite-to-ground communication is proposed. Most of the machine learning models for OAM mode detection reported in literature directly take intensity and phase images of OAM modes as inputs. A novel attempt is made in the proposed work, wherein Histogram of Gradients (HOG) features are extracted from these images and fed to machine learning models. Two architectures are proposed in this paper for OAM mode detection and their performances are reported. The performances of proposed models are also compared under different atmospheric turbulence conditions, propagation distances and the results are reported. In order to evaluate the efficacy of proposed models, performance results of OAM mode detection using various other methods reported in literature are compared with the results obtained from proposed work. It is observed that the performance of proposed models are almost on par with the models reported in literature. Maximum recognition accuracy of 100% with a prediction time ranging between 83 - 157ms, was achieved using the proposed models. The proposed OAM mode detection models can be used for various other quantum communication applications too, including underwater communication.

International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS)•Dec 21, 2022•2 citations

Correlation-Pattern-Based Orbital Angular Momentum Entanglement Measurement Through Neural Networks

Jiaxian Zhao, Zhifeng Liu, Chenghou Tu +2 more

Abstract High-dimensional (HD) entanglement of photonic orbital angular momentum (OAM) is pivotal for advancing quantum communication and information processing, but its characterization remains significant challenges due to the complexity of quantum state tomography and experimental limitations such as low photon counts caused by losses. Here, we propose a pre-trained physics-informed neural network (PTPINN) framework that enables efficient and rapid reconstruction of HD-OAM entangled states under low photon counts. Experimental results show that the fidelity of five-dimensional OAM entanglement reaches F = 0.958 ± 0.010 even with an exposure time as short as 50 ms. This highlights the capability of PTPINN to achieve high-precision quantum state reconstruction with limited photons, owing to its innovative designs, thus overcoming the reliance on high photon counts typical of traditional methods. Our method provides a practical and scalable solution for high-fidelity characterization of HD-OAM entanglement in environments with low photon numbers and high noise, paving the way for robust long-distance quantum information transmission.

Chinese Physics Letters•Feb 24, 2025•0 citations

Machine-learning-assisted efficient reconstruction of the quantum states generated from the Sagnac polarization-entangled photon source

Menghui Mao, Wei 唯 Zhou 周, Xinhui Li +3 more

Abstract Neural networks are becoming ubiquitous in various areas of physics as a successful machine learning (ML) technique for addressing different tasks. Based on ML technique, we propose and experimentally demonstrate an efficient method for state reconstruction of the widely used Sagnac polarization-entangled photon source. By properly modeling the target states, a multi-output fully connected neural network is well trained using only six of the sixteen measurement bases in standard tomography technique, and hence our method reduces the resource consumption without loss of accuracy. We demonstrate the ability of the neural network to predict state parameters with a high precision by using both simulated and experimental data. Explicitly, the mean absolute error for all the parameters is below 0.05 for the simulated data and a mean fidelity of 0.99 is achieved for experimentally generated states. Our method could be generalized to estimate other kinds of states, as well as other quantum information tasks.

Chinese Physics B•May 30, 2024•1 citation
The Bell state is a crucial resource for the realization of quantum information tasks, and when combined with orbital angular momentum (OAM), it enables a high-dimensional Hilbert space, which is essential for high-capacity quantum communication. In this study, we demonstrate the recognition of OAM Bell states using interference patterns generated by a classical light source and a single-photon source from a Sagnac interferometer-based OAM Bell state evolution device. The interference patterns exhibit a one-to-one correspondence with the input Bell states, providing conclusive evidence for the full recognition of OAM Bell states. Furthermore, we introduce machine learning to the field of Bell state recognition by proposing a neural network model capable of accurately recognizing higher order single-photon OAM Bell states, even in the undersampling case. In particular, the model’s training set includes interference patterns of OAM Bell states generated by classical light sources, yet it is able to recognize single-photon OAM Bell states with high accuracy, without relying on quantum resources during training. Our innovative application of neural networks to the recognition of single-photon OAM Bell states not only circumvents the resource consumption and experimental difficulties associated with quantum light sources but also facilitates the study of OAM-based quantum information.
Bell states are the most fundamental resource in realizing quantum information tasks and have a very unique position in quantum mechanics. Utilizing orbital angular momentum (OAM) to encode single-photon Bell states enables the realization of high-dimensional Hilbert space, which is crucial for the field of quantum information. In this paper, we design a single-photon OAM Bell-state evolution device based on the Sagnac interferometer, which can make one-to-one correspondence between the input Bell states and the output states. Moreover, we also develop a single-photon single-pixel imaging (SPI) technique, which improves spatial resolution and decreases acquisition time in the meantime, to capture interference images of output states. The results show that single-photon OAM Bell states can be fully recognized by comparing the differences of interference images. We innovatively utilize the SPI technique for single-photon OAM Bell-state recognition. This indicates that the SPI technique effectively promotes the study of quantum information based on OAM, while the quantum information based on OAM provides a clear application scenario for the SPI technique.
The generation of light containing large degrees of orbital angular momentum (OAM) has recently been demon- strated in both the classical and quantum regimes. Since there is no fundamental limit to how many quanta of OAM a single photon can carry, optical states with an arbitrarily high difference in this quantum number may, in principle, be entangled. This opens the door to investigations into high-dimensional entanglement shared between states in superpositions of nonzero OAM. Additionally, making use of non-zero OAM states can allow for a dramatic increase in the amount of information carried by a single photon, thus increasing the information capacity of a communication channel. In practice, however, it is difficult to differentiate between states with high OAM numbers with high precision. Here we investigate the ability of deep neural networks to differentiate between states that contain large values of OAM. We show that such networks may be used to differentiate be- tween nearby OAM states that contain realistic amounts of noise, with OAM values of up to 100. Additionally, we examine how the classification accuracy scales with the signal-to-noise ratio of images that are used to train the network, as well as those being tested. Finally, we demonstrate the simultaneous classification of < 100 OAM states with greater than 70 % accuracy. We intend to verify our system with experimentally-produced classi- cal OAM states, as well as investigate possibilities that would allow this technique to work in the few-photon quantum regime.
Orbital angular momentum (OAM) entanglement states have great potential in enhancing the information capacity in quantum communications. To make full use of the OAM degree of freedom, the measurement and distinction of OAM Bell states become a key step that needs to be accomplished. However, there is still no solution to achieve complete distinction of OAM Bell states at the single-photon level. Here we demonstrate the complete OAM Bell-state measurement without auxiliary photons by using linear optics. Furthermore, we propose a quantum communication network via OAM Bell-state multiplexing, perform a proof-of-principle experiment in the first- and second-order OAM subspaces for two users, and achieve average success probabilities of obtaining information of 91.6% for User-I and 89.1% for User-II. In principle, our scheme allows more users to be added by using high-order OAM Bell states. Our research extends the manipulation method for high-dimensional quantum states and paves the way for the application of OAM multiplexing in quantum communications.
Orbital angular momentum (OAM) of light has enabled quantum encoding in higher dimensional Hilbert spaces, opening up new opportunities for high capacity satellite-to-ground quantum communications. In this paper, machine learning based recognition of OAM modes for satellite-to-ground communication is proposed. Most of the machine learning models for OAM mode detection reported in literature directly take intensity and phase images of OAM modes as inputs. A novel attempt is made in the proposed work, wherein Histogram of Gradients (HOG) features are extracted from these images and fed to machine learning models. Two architectures are proposed in this paper for OAM mode detection and their performances are reported. The performances of proposed models are also compared under different atmospheric turbulence conditions, propagation distances and the results are reported. In order to evaluate the efficacy of proposed models, performance results of OAM mode detection using various other methods reported in literature are compared with the results obtained from proposed work. It is observed that the performance of proposed models are almost on par with the models reported in literature. Maximum recognition accuracy of 100% with a prediction time ranging between 83 - 157ms, was achieved using the proposed models. The proposed OAM mode detection models can be used for various other quantum communication applications too, including underwater communication.
Abstract High-dimensional (HD) entanglement of photonic orbital angular momentum (OAM) is pivotal for advancing quantum communication and information processing, but its characterization remains significant challenges due to the complexity of quantum state tomography and experimental limitations such as low photon counts caused by losses. Here, we propose a pre-trained physics-informed neural network (PTPINN) framework that enables efficient and rapid reconstruction of HD-OAM entangled states under low photon counts. Experimental results show that the fidelity of five-dimensional OAM entanglement reaches F = 0.958 ± 0.010 even with an exposure time as short as 50 ms. This highlights the capability of PTPINN to achieve high-precision quantum state reconstruction with limited photons, owing to its innovative designs, thus overcoming the reliance on high photon counts typical of traditional methods. Our method provides a practical and scalable solution for high-fidelity characterization of HD-OAM entanglement in environments with low photon numbers and high noise, paving the way for robust long-distance quantum information transmission.
Abstract Neural networks are becoming ubiquitous in various areas of physics as a successful machine learning (ML) technique for addressing different tasks. Based on ML technique, we propose and experimentally demonstrate an efficient method for state reconstruction of the widely used Sagnac polarization-entangled photon source. By properly modeling the target states, a multi-output fully connected neural network is well trained using only six of the sixteen measurement bases in standard tomography technique, and hence our method reduces the resource consumption without loss of accuracy. We demonstrate the ability of the neural network to predict state parameters with a high precision by using both simulated and experimental data. Explicitly, the mean absolute error for all the parameters is below 0.05 for the simulated data and a mean fidelity of 0.99 is achieved for experimentally generated states. Our method could be generalized to estimate other kinds of states, as well as other quantum information tasks.