Implicit neural representation(INR)networks break through the accuracy and resolution limitations of traditional discrete representations by modeling high-dimensional data as continuously differentiable implicit neura...Implicit neural representation(INR)networks break through the accuracy and resolution limitations of traditional discrete representations by modeling high-dimensional data as continuously differentiable implicit neural networks,enabling lossless compression and efficient reconstruction of details in a compact form.However,an optical-assisted INR network has yet to be demonstrated.INR networks require high nonlinearity,whereas implementing analog nonlinear activation in photonic neural networks is a challenge.Inspired by the inherent physical properties of modulators,we propose an optoelectronic nonlinear activation and implement it on the image reconstruction task.Simulations and experiments demonstrate that the proposed optoelectronic periodic neural network can represent images and perform image reconstruction with excellent results.This approach empowers complex image reconstruction with high-frequency details and reduces the amount of required hardware.Our method enables the development of compact,efficient optoelectronic neural networks,utilizing repeatable modular units for scalable and practical high-performance computing.It can enable scene generation and compression in biomedicine,autonomous driving,and augmented reality/virtual reality.展开更多
Parallel multi-thread processing in advanced intelligent processors is the core to realize high-speed and high-capacity signal processing systems.Optical neural network(ONN)has the native advantages of high paralleliz...Parallel multi-thread processing in advanced intelligent processors is the core to realize high-speed and high-capacity signal processing systems.Optical neural network(ONN)has the native advantages of high parallelization,large bandwidth,and low power consumption to meet the demand of big data.Here,we demonstrate the dual-layer ONN with Mach-Zehnder interferometer(MZI)network and nonlinear layer,while the nonlinear activation function is achieved by optical-electronic signal conversion.Two frequency components from the microcomb source carrying digit datasets are simultaneously imposed and intelligently recognized through the ONN.We successfully achieve the digit classification of different frequency components by demultiplexing the output signal and testing power distribution.Efficient parallelization feasibility with wavelength division multiplexing is demonstrated in our high-dimensional ONN.This work provides a high-performance architecture for future parallel high-capacity optical analog computing.展开更多
Optical neural networks are emerging as a competitive alternative to their electronic counterparts,offering distinct advantages in bandwidth and energy efficiency.Despite these benefits,scaling up on-chip optical neur...Optical neural networks are emerging as a competitive alternative to their electronic counterparts,offering distinct advantages in bandwidth and energy efficiency.Despite these benefits,scaling up on-chip optical neural networks for end-to-end inference is facing significant challenges.First,network depth is constrained by the weak cascadability of optical nonlinear activation functions.Second,the input size is constrained by the scale of the optical matrix.Herein,we propose a scaling up strategy called partially coherent deep optical neural networks(PDONNs).By leveraging an on-chip nonlinear activation function based on opto-electro-opto conversion,PDONN enables network depth expansion with positive net gain.Additionally,convolutional layers achieve rapid dimensionality reduction,thereby allowing for an increase in the accommodated input size.The use of a partially coherent optical source significantly reduces reliance on narrow-linewidth laser diodes and coherent detection.Owing to their broader spectral characteristics and simpler implementation,such sources are more accessible and compatible with scalable integration.Benefiting from these innovations,we designed and fabricated a monolithically integrated optical neural network with the largest input size and the deepest network depth,comprising an input layer with a size of 64,two convolutional layers,and two fully connected layers.We successfully demonstrate end-to-end two-class classification of fashion images and four-class classification of handwritten digits with accuracies of 96%and 94%,respectively,using an in-situ training method.Notably,performance is well maintained with partially coherent illumination.This proposed architecture represents a critical step toward realizing energy-efficient,scalable,and widely accessible optical computing.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.62305184)the Basic and Applied Basic Research Foundation of Guangdong Province(Grant No.2023A1515012932)+1 种基金the Science,Technology and Innovation Commission of Shenzhen Municipality(Grant No.JCYJ20241202123919027)the Science,Technology and Innovation Commission of Shenzhen Municipality(Grant No.WDZC20220818100259004).
文摘Implicit neural representation(INR)networks break through the accuracy and resolution limitations of traditional discrete representations by modeling high-dimensional data as continuously differentiable implicit neural networks,enabling lossless compression and efficient reconstruction of details in a compact form.However,an optical-assisted INR network has yet to be demonstrated.INR networks require high nonlinearity,whereas implementing analog nonlinear activation in photonic neural networks is a challenge.Inspired by the inherent physical properties of modulators,we propose an optoelectronic nonlinear activation and implement it on the image reconstruction task.Simulations and experiments demonstrate that the proposed optoelectronic periodic neural network can represent images and perform image reconstruction with excellent results.This approach empowers complex image reconstruction with high-frequency details and reduces the amount of required hardware.Our method enables the development of compact,efficient optoelectronic neural networks,utilizing repeatable modular units for scalable and practical high-performance computing.It can enable scene generation and compression in biomedicine,autonomous driving,and augmented reality/virtual reality.
基金Peng Xie acknowledges the support from the China Scholarship Council(Grant no.201804910829).
文摘Parallel multi-thread processing in advanced intelligent processors is the core to realize high-speed and high-capacity signal processing systems.Optical neural network(ONN)has the native advantages of high parallelization,large bandwidth,and low power consumption to meet the demand of big data.Here,we demonstrate the dual-layer ONN with Mach-Zehnder interferometer(MZI)network and nonlinear layer,while the nonlinear activation function is achieved by optical-electronic signal conversion.Two frequency components from the microcomb source carrying digit datasets are simultaneously imposed and intelligently recognized through the ONN.We successfully achieve the digit classification of different frequency components by demultiplexing the output signal and testing power distribution.Efficient parallelization feasibility with wavelength division multiplexing is demonstrated in our high-dimensional ONN.This work provides a high-performance architecture for future parallel high-capacity optical analog computing.
基金supported by the Fundamental Research Funds for the Central Universities.
文摘Optical neural networks are emerging as a competitive alternative to their electronic counterparts,offering distinct advantages in bandwidth and energy efficiency.Despite these benefits,scaling up on-chip optical neural networks for end-to-end inference is facing significant challenges.First,network depth is constrained by the weak cascadability of optical nonlinear activation functions.Second,the input size is constrained by the scale of the optical matrix.Herein,we propose a scaling up strategy called partially coherent deep optical neural networks(PDONNs).By leveraging an on-chip nonlinear activation function based on opto-electro-opto conversion,PDONN enables network depth expansion with positive net gain.Additionally,convolutional layers achieve rapid dimensionality reduction,thereby allowing for an increase in the accommodated input size.The use of a partially coherent optical source significantly reduces reliance on narrow-linewidth laser diodes and coherent detection.Owing to their broader spectral characteristics and simpler implementation,such sources are more accessible and compatible with scalable integration.Benefiting from these innovations,we designed and fabricated a monolithically integrated optical neural network with the largest input size and the deepest network depth,comprising an input layer with a size of 64,two convolutional layers,and two fully connected layers.We successfully demonstrate end-to-end two-class classification of fashion images and four-class classification of handwritten digits with accuracies of 96%and 94%,respectively,using an in-situ training method.Notably,performance is well maintained with partially coherent illumination.This proposed architecture represents a critical step toward realizing energy-efficient,scalable,and widely accessible optical computing.
