- Special Issue
- Deep learning in photonics
- 29 Article (s)
Deep learning in photonics: introduction
Li Gao, Yang Chai, Darko Zibar, and Zongfu Yu
The connection between Maxwell’s equations and neural networks opens unprecedented opportunities at the interface between photonics and deep learning. This feature issue highlights recent research progress at the interdisciplinary field of photonics and deep learning and provides an opportunity for different communities to exchange their ideas from different perspectives. The connection between Maxwell’s equations and neural networks opens unprecedented opportunities at the interface between photonics and deep learning. This feature issue highlights recent research progress at the interdisciplinary field of photonics and deep learning and provides an opportunity for different communities to exchange their ideas from different perspectives.
Photonics Research
- Publication Date: Jul. 19, 2021
- Vol. 9, Issue 8, 0800DLP1 (2021)
Modulation format identification in fiber communications using single dynamical node-based photonic reservoir computing
Qiang Cai, Ya Guo, Pu Li, Adonis Bogris, K. Alan Shore, Yamei Zhang, and Yuncai Wang
We present a simple approach based on photonic reservoir computing (P-RC) for modulation format identification (MFI) in optical fiber communications. Here an optically injected semiconductor laser with self-delay feedback is trained with the representative features from the asynchronous amplitude histograms of modulation signals. Numerical simulations are conducted for three widely used modulation formats (on–off keying, differential phase-shift keying, and quadrature amplitude modulation) for various transmission situations where the optical signal-to-noise ratio varies from 12 to 26 dB, the chromatic dispersion varies from -500 to 500 ps/nm, and the differential group delay varies from 0 to 20 ps. Under these situations, final simulation results demonstrate that this technique can efficiently identify all those modulation formats with an accuracy of >95% after optimizing the control parameters of the P-RC layer such as the injection strength, feedback strength, bias current, and frequency detuning. The proposed technique utilizes very simple devices and thus offers a resource-efficient alternative approach to MFI. We present a simple approach based on photonic reservoir computing (P-RC) for modulation format identification (MFI) in optical fiber communications. Here an optically injected semiconductor laser with self-delay feedback is trained with the representative features from the asynchronous amplitude histograms of modulation signals. Numerical simulations are conducted for three widely used modulation formats (on–off keying, differential phase-shift keying, and quadrature amplitude modulation) for various transmission situations where the optical signal-to-noise ratio varies from 12 to 26 dB, the chromatic dispersion varies from -500 to 500 ps/nm, and the differential group delay varies from 0 to 20 ps. Under these situations, final simulation results demonstrate that this technique can efficiently identify all those modulation formats with an accuracy of >95% after optimizing the control parameters of the P-RC layer such as the injection strength, feedback strength, bias current, and frequency detuning. The proposed technique utilizes very simple devices and thus offers a resource-efficient alternative approach to MFI.
Photonics Research
- Publication Date: Dec. 24, 2020
- Vol. 9, Issue 1, 010000B1 (2021)
Integrating deep learning to achieve phase compensation for free-space orbital-angular-momentum-encoded quantum key distribution under atmospheric turbulence
Xingyu Wang, Tianyi Wu, Chen Dong, Haonan Zhu, Zhuodan Zhu, and Shanghong Zhao
A high-dimensional quantum key distribution (QKD), which adopts degrees of freedom of the orbital angular momentum (OAM) states, is beneficial to realize secure and high-speed QKD. However, the helical phase of a vortex beam that carries OAM is sensitive to the atmospheric turbulence and easily distorted. In this paper, an adaptive compensation method using deep learning technology is developed to improve the performance of OAM-encoded QKD schemes. A convolutional neural network model is first trained to learn the mapping relationship of intensity profiles of inputs and the turbulent phase, and such mapping is used as feedback to control a spatial light modulator to generate a phase screen to correct the distorted vortex beam. Then an OAM-encoded QKD scheme with the capability of real-time phase correction is designed, in which the compensation module only needs to extract the intensity distributions of the Gaussian probe beam and thus ensures that the information encoded on OAM states would not be eavesdropped. The results show that our method can efficiently improve the mode purity of the encoded OAM states and extend the secure distance for the involved QKD protocols in the free-space channel, which is not limited to any specific QKD protocol. A high-dimensional quantum key distribution (QKD), which adopts degrees of freedom of the orbital angular momentum (OAM) states, is beneficial to realize secure and high-speed QKD. However, the helical phase of a vortex beam that carries OAM is sensitive to the atmospheric turbulence and easily distorted. In this paper, an adaptive compensation method using deep learning technology is developed to improve the performance of OAM-encoded QKD schemes. A convolutional neural network model is first trained to learn the mapping relationship of intensity profiles of inputs and the turbulent phase, and such mapping is used as feedback to control a spatial light modulator to generate a phase screen to correct the distorted vortex beam. Then an OAM-encoded QKD scheme with the capability of real-time phase correction is designed, in which the compensation module only needs to extract the intensity distributions of the Gaussian probe beam and thus ensures that the information encoded on OAM states would not be eavesdropped. The results show that our method can efficiently improve the mode purity of the encoded OAM states and extend the secure distance for the involved QKD protocols in the free-space channel, which is not limited to any specific QKD protocol.
Photonics Research
- Publication Date: Jan. 13, 2021
- Vol. 9, Issue 2, 020000B9 (2021)
Deep plug-and-play priors for spectral snapshot compressive imaging
Siming Zheng, Yang Liu, Ziyi Meng, Mu Qiao, Zhishen Tong, Xiaoyu Yang, Shensheng Han, and Xin Yuan
We propose a plug-and-play (PnP) method that uses deep-learning-based denoisers as regularization priors for spectral snapshot compressive imaging (SCI). Our method is efficient in terms of reconstruction quality and speed trade-off, and flexible enough to be ready to use for different compressive coding mechanisms. We demonstrate the efficiency and flexibility in both simulations and five different spectral SCI systems and show that the proposed deep PnP prior could achieve state-of-the-art results with a simple plug-in based on the optimization framework. This paves the way for capturing and recovering multi- or hyperspectral information in one snapshot, which might inspire intriguing applications in remote sensing, biomedical science, and material science. Our code is available at: https://github.com/zsm1211/PnP-CASSI. We propose a plug-and-play (PnP) method that uses deep-learning-based denoisers as regularization priors for spectral snapshot compressive imaging (SCI). Our method is efficient in terms of reconstruction quality and speed trade-off, and flexible enough to be ready to use for different compressive coding mechanisms. We demonstrate the efficiency and flexibility in both simulations and five different spectral SCI systems and show that the proposed deep PnP prior could achieve state-of-the-art results with a simple plug-in based on the optimization framework. This paves the way for capturing and recovering multi- or hyperspectral information in one snapshot, which might inspire intriguing applications in remote sensing, biomedical science, and material science. Our code is available at: https://github.com/zsm1211/PnP-CASSI.
Photonics Research
- Publication Date: Jan. 21, 2021
- Vol. 9, Issue 2, 02000B18 (2021)
High-fidelity image reconstruction for compressed ultrafast photography via an augmented-Lagrangian and deep-learning hybrid algorithm
Chengshuai Yang, Yunhua Yao, Chengzhi Jin, Dalong Qi, Fengyan Cao, Yilin He, Jiali Yao, Pengpeng Ding, Liang Gao, Tianqing Jia, Jinyang Liang, Zhenrong Sun, and Shian Zhang
Compressed ultrafast photography (CUP) is the fastest single-shot passive ultrafast optical imaging technique, which has shown to be a powerful tool in recording self-luminous or non-repeatable ultrafast phenomena. However, the low fidelity of image reconstruction based on the conventional augmented-Lagrangian (AL) and two-step iterative shrinkage/thresholding (TwIST) algorithms greatly prevents practical applications of CUP, especially for those ultrafast phenomena that need high spatial resolution. Here, we develop a novel AL and deep-learning (DL) hybrid (i.e., AL+DL) algorithm to realize high-fidelity image reconstruction for CUP. The AL+DL algorithm not only optimizes the sparse domain and relevant iteration parameters via learning the dataset but also simplifies the mathematical architecture, so it greatly improves the image reconstruction accuracy. Our theoretical simulation and experimental results validate the superior performance of the AL+DL algorithm in image fidelity over conventional AL and TwIST algorithms, where the peak signal-to-noise ratio and structural similarity index can be increased at least by 4 dB (9 dB) and 0.1 (0.05) for a complex (simple) dynamic scene, respectively. This study can promote the applications of CUP in related fields, and it will also enable a new strategy for recovering high-dimensional signals from low-dimensional detection. Compressed ultrafast photography (CUP) is the fastest single-shot passive ultrafast optical imaging technique, which has shown to be a powerful tool in recording self-luminous or non-repeatable ultrafast phenomena. However, the low fidelity of image reconstruction based on the conventional augmented-Lagrangian (AL) and two-step iterative shrinkage/thresholding (TwIST) algorithms greatly prevents practical applications of CUP, especially for those ultrafast phenomena that need high spatial resolution. Here, we develop a novel AL and deep-learning (DL) hybrid (i.e., AL+DL) algorithm to realize high-fidelity image reconstruction for CUP. The AL+DL algorithm not only optimizes the sparse domain and relevant iteration parameters via learning the dataset but also simplifies the mathematical architecture, so it greatly improves the image reconstruction accuracy. Our theoretical simulation and experimental results validate the superior performance of the AL+DL algorithm in image fidelity over conventional AL and TwIST algorithms, where the peak signal-to-noise ratio and structural similarity index can be increased at least by 4 dB (9 dB) and 0.1 (0.05) for a complex (simple) dynamic scene, respectively. This study can promote the applications of CUP in related fields, and it will also enable a new strategy for recovering high-dimensional signals from low-dimensional detection.
Photonics Research
- Publication Date: Jan. 21, 2021
- Vol. 9, Issue 2, 02000B30 (2021)
Smart ring resonator–based sensor for multicomponent chemical analysis via machine learning
Zhenyu Li, Hui Zhang, Binh Thi Thanh Nguyen, Shaobo Luo, Patricia Yang Liu, Jun Zou, Yuzhi Shi, Hong Cai, Zhenchuan Yang, Yufeng Jin, Yilong Hao, Yi Zhang, and Ai-Qun Liu
We demonstrate a smart sensor for label-free multicomponent chemical analysis using a single label-free ring resonator to acquire the entire resonant spectrum of the mixture and a neural network model to predict the composition for multicomponent analysis. The smart sensor shows a high prediction accuracy with a low root-mean-squared error ranging only from 0.13 to 2.28 mg/mL. The predicted concentrations of each component in the testing dataset almost all fall within the 95% prediction bands. With its simple label-free detection strategy and high accuracy, the smart sensor promises great potential for multicomponent analysis applications in many fields. We demonstrate a smart sensor for label-free multicomponent chemical analysis using a single label-free ring resonator to acquire the entire resonant spectrum of the mixture and a neural network model to predict the composition for multicomponent analysis. The smart sensor shows a high prediction accuracy with a low root-mean-squared error ranging only from 0.13 to 2.28 mg/mL. The predicted concentrations of each component in the testing dataset almost all fall within the 95% prediction bands. With its simple label-free detection strategy and high accuracy, the smart sensor promises great potential for multicomponent analysis applications in many fields.
Photonics Research
- Publication Date: Jan. 21, 2021
- Vol. 9, Issue 2, 02000B38 (2021)
Monte Carlo simulation fused with target distribution modeling via deep reinforcement learning for automatic high-efficiency photon distribution estimation
Jianhui Ma, Zun Piao, Shuang Huang, Xiaoman Duan, Genggeng Qin, Linghong Zhou, and Yuan Xu
Particle distribution estimation is an important issue in medical diagnosis. In particular, photon scattering in some medical devices extremely degrades image quality and causes measurement inaccuracy. The Monte Carlo (MC) algorithm is regarded as the most accurate particle estimation approach but is still time-consuming, even with graphic processing unit (GPU) acceleration. The goal of this work is to develop an automatic scatter estimation framework for high-efficiency photon distribution estimation. Specifically, a GPU-based MC simulation initially yields a raw scatter signal with a low photon number to hasten scatter generation. In the proposed method, assume that the scatter signal follows Poisson distribution, where an optimization objective function fused with sparse feature penalty is modeled. Then, an over-relaxation algorithm is deduced mathematically to solve this objective function. For optimizing the parameters in the over-relaxation algorithm, the deep Q-network in the deep reinforcement learning scheme is built to intelligently interact with the over-relaxation algorithm to accurately and rapidly estimate a scatter signal with the large range of photon numbers. Experimental results demonstrated that our proposed framework can achieve superior performance with structural similarity >0.94, peak signal-to-noise ratio >26.55 dB, and relative absolute error <5.62%, and the lowest computation time for one scatter image generation can be within 2 s. Particle distribution estimation is an important issue in medical diagnosis. In particular, photon scattering in some medical devices extremely degrades image quality and causes measurement inaccuracy. The Monte Carlo (MC) algorithm is regarded as the most accurate particle estimation approach but is still time-consuming, even with graphic processing unit (GPU) acceleration. The goal of this work is to develop an automatic scatter estimation framework for high-efficiency photon distribution estimation. Specifically, a GPU-based MC simulation initially yields a raw scatter signal with a low photon number to hasten scatter generation. In the proposed method, assume that the scatter signal follows Poisson distribution, where an optimization objective function fused with sparse feature penalty is modeled. Then, an over-relaxation algorithm is deduced mathematically to solve this objective function. For optimizing the parameters in the over-relaxation algorithm, the deep Q-network in the deep reinforcement learning scheme is built to intelligently interact with the over-relaxation algorithm to accurately and rapidly estimate a scatter signal with the large range of photon numbers. Experimental results demonstrated that our proposed framework can achieve superior performance with structural similarity >0.94, peak signal-to-noise ratio >26.55 dB, and relative absolute error <5.62%, and the lowest computation time for one scatter image generation can be within 2 s.
Photonics Research
- Publication Date: Feb. 08, 2021
- Vol. 9, Issue 3, 03000B45 (2021)
Deep compressed imaging via optimized pattern scanning|On the Cover
Kangning Zhang, Junjie Hu, and Weijian Yang
The need for high-speed imaging in applications such as biomedicine, surveillance, and consumer electronics has called for new developments of imaging systems. While the industrial effort continuously pushes the advance of silicon focal plane array image sensors, imaging through a single-pixel detector has gained significant interest thanks to the development of computational algorithms. Here, we present a new imaging modality, deep compressed imaging via optimized-pattern scanning, which can significantly increase the acquisition speed for a single-detector-based imaging system. We project and scan an illumination pattern across the object and collect the sampling signal with a single-pixel detector. We develop an innovative end-to-end optimized auto-encoder, using a deep neural network and compressed sensing algorithm, to optimize the illumination pattern, which allows us to reconstruct faithfully the image from a small number of measurements, with a high frame rate. Compared with the conventional switching-mask-based single-pixel camera and point-scanning imaging systems, our method achieves a much higher imaging speed, while retaining a similar imaging quality. We experimentally validated this imaging modality in the settings of both continuous-wave illumination and pulsed light illumination and showed high-quality image reconstructions with a high compressed sampling rate. This new compressed sensing modality could be widely applied in different imaging systems, enabling new applications that require high imaging speeds. The need for high-speed imaging in applications such as biomedicine, surveillance, and consumer electronics has called for new developments of imaging systems. While the industrial effort continuously pushes the advance of silicon focal plane array image sensors, imaging through a single-pixel detector has gained significant interest thanks to the development of computational algorithms. Here, we present a new imaging modality, deep compressed imaging via optimized-pattern scanning, which can significantly increase the acquisition speed for a single-detector-based imaging system. We project and scan an illumination pattern across the object and collect the sampling signal with a single-pixel detector. We develop an innovative end-to-end optimized auto-encoder, using a deep neural network and compressed sensing algorithm, to optimize the illumination pattern, which allows us to reconstruct faithfully the image from a small number of measurements, with a high frame rate. Compared with the conventional switching-mask-based single-pixel camera and point-scanning imaging systems, our method achieves a much higher imaging speed, while retaining a similar imaging quality. We experimentally validated this imaging modality in the settings of both continuous-wave illumination and pulsed light illumination and showed high-quality image reconstructions with a high compressed sampling rate. This new compressed sensing modality could be widely applied in different imaging systems, enabling new applications that require high imaging speeds.
Photonics Research
- Publication Date: Mar. 01, 2021
- Vol. 9, Issue 3, 03000B57 (2021)
Backpropagation through nonlinear units for the all-optical training of neural networks
Xianxin Guo, Thomas D. Barrett, Zhiming M. Wang, and A. I. Lvovsky
We propose a practical scheme for end-to-end optical backpropagation in neural networks. Using saturable absorption for the nonlinear units, we find that the backward-propagating gradients required to train the network can be approximated in a surprisingly simple pump-probe scheme that requires only simple passive optical elements. Simulations show that, with readily obtainable optical depths, our approach can achieve equivalent performance to state-of-the-art computational networks on image classification benchmarks, even in deep networks with multiple sequential gradient approximation. With backpropagation through nonlinear units being an outstanding challenge to the field, this work provides a feasible path toward truly all-optical neural networks. We propose a practical scheme for end-to-end optical backpropagation in neural networks. Using saturable absorption for the nonlinear units, we find that the backward-propagating gradients required to train the network can be approximated in a surprisingly simple pump-probe scheme that requires only simple passive optical elements. Simulations show that, with readily obtainable optical depths, our approach can achieve equivalent performance to state-of-the-art computational networks on image classification benchmarks, even in deep networks with multiple sequential gradient approximation. With backpropagation through nonlinear units being an outstanding challenge to the field, this work provides a feasible path toward truly all-optical neural networks.
Photonics Research
- Publication Date: Mar. 01, 2021
- Vol. 9, Issue 3, 03000B71 (2021)
Learning to recognize misaligned hyperfine orbital angular momentum modes
Xiao Wang, Yufeng Qian, JingJing Zhang, Guangdong Ma, Shupeng Zhao, RuiFeng Liu, Hongrong Li, Pei Zhang, Hong Gao, Feng Huang, and Fuli Li
Orbital angular momentum (OAM)-carrying beams have received extensive attention due to their high-dimensional characteristics in the context of free-space optical communication. However, accurate OAM mode recognition still suffers from reference misalignment of lateral displacement, beam waist size, and initial phase. Here we propose a deep-learning method to exquisitely recognize OAM modes under misalignment by using an alignment-free fractal multipoint interferometer. Our experiments achieve 98.35% recognizing accuracy when strong misalignment is added to hyperfine OAM modes whose Bures distance is 0.01. The maximum lateral displacement we added with respect to the perfectly on-axis beam is about ±0.5 beam waist size. This work offers a superstable proposal for OAM mode recognition in the application of free-space optical communication and allows an increase of the communication capacity. Orbital angular momentum (OAM)-carrying beams have received extensive attention due to their high-dimensional characteristics in the context of free-space optical communication. However, accurate OAM mode recognition still suffers from reference misalignment of lateral displacement, beam waist size, and initial phase. Here we propose a deep-learning method to exquisitely recognize OAM modes under misalignment by using an alignment-free fractal multipoint interferometer. Our experiments achieve 98.35% recognizing accuracy when strong misalignment is added to hyperfine OAM modes whose Bures distance is 0.01. The maximum lateral displacement we added with respect to the perfectly on-axis beam is about ±0.5 beam waist size. This work offers a superstable proposal for OAM mode recognition in the application of free-space optical communication and allows an increase of the communication capacity.
Photonics Research
- Publication Date: Mar. 15, 2021
- Vol. 9, Issue 4, 04000B81 (2021)
Guest Editors:
Zongfu Yu,
University of Wisconsin, Madison, USA (Lead Editor)
Yang Chai,
The Hong Kong Polytechnic University, China
Li Gao,
Nanjing University of Posts and Telecommunications, China
Darko Zibar,
Technical University of Denmark, Denmark
On the Cover for this virtual special issue
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20