Photonic neural networks(PNNs)of sufficiently large physical dimensions and high operation accuracies are envisaged as ideal candidates for breaking the major bottlenecks in the current artificial intelligence archite...Photonic neural networks(PNNs)of sufficiently large physical dimensions and high operation accuracies are envisaged as ideal candidates for breaking the major bottlenecks in the current artificial intelligence architectures in terms of latency,energy efficiency,and computational power.To achieve this vision,it is of vital importance to scale up the PNNs while simultaneously reducing the high demand on the dimensions required by them.The underlying cause of this strategy is the enormous gap between the scales of photonic and electronic integrated circuits.Here,we demonstrate monolithically integrated optical convolutional processors on thin film lithium niobate(TFLN)that harness inherent parallelism in photonics to enable large-scale programmable convolution kernels and,in turn,greatly reduce the dimensions required by subsequent fully connected layers.Experimental validation achieves high classification accuracies of 96%(86%)on the MNIST(Fashion-MNIST)dataset and 84.6%on the AG News dataset while dramatically reducing the required subsequent fully connected layer dimensions to 196×10(from 784×10)and 175×4(from 800×4),respectively.Furthermore,our devices can be driven by commercial field-programmable gate array systems;a unique advantage in addition to their scalable channel number and kernel size.Our architecture provides a solution to build practical machine learning photonic devices.展开更多
We report the fabrication of an 8-meter-long thin-flm lithium niobate optical true delay line using the photolithography-assisted chemomechanical etching technique,showing a low transmission loss of 0.036 dB/cm in the...We report the fabrication of an 8-meter-long thin-flm lithium niobate optical true delay line using the photolithography-assisted chemomechanical etching technique,showing a low transmission loss of 0.036 dB/cm in the conventional telecom band.展开更多
We present a compact optical delay line(ODL)with wide-range continuous tunability on thin-film lithium niobate platform.The proposed device integrates an unbalanced Mach-Zehnder interferometer(MZI)architecture with du...We present a compact optical delay line(ODL)with wide-range continuous tunability on thin-film lithium niobate platform.The proposed device integrates an unbalanced Mach-Zehnder interferometer(MZI)architecture with dual tunable couplers,where each coupler comprises two 2×2 multimode interferometers and a MZI phase-tuning section.Experimental results demonstrate continuous delay tuning from 0 to 293 ps through synchronized control of coupling coefficients,corresponding to a 4 cm path difference between interferometer arms.The measured delay range exhibits excellent agreement with theoretical predictions derived from ODL waveguide parameters.This result addresses critical challenges in integrated photonic systems that require precise temporal control,particularly for applications in optical communications and quantum information processing,where a wide tuning range is paramount.展开更多
基金supported by the National Natural Science Foundation of China (Grant Nos.12192251,12334014,62335019,12134001,1230441812474378)+1 种基金the Quantum Science and Technology National Science and Technology Major Project(Grant No.2021ZD0301403)the Shanghai Municipal Science and Technology Major Project (Grant No.2019SHZDZX01)。
文摘Photonic neural networks(PNNs)of sufficiently large physical dimensions and high operation accuracies are envisaged as ideal candidates for breaking the major bottlenecks in the current artificial intelligence architectures in terms of latency,energy efficiency,and computational power.To achieve this vision,it is of vital importance to scale up the PNNs while simultaneously reducing the high demand on the dimensions required by them.The underlying cause of this strategy is the enormous gap between the scales of photonic and electronic integrated circuits.Here,we demonstrate monolithically integrated optical convolutional processors on thin film lithium niobate(TFLN)that harness inherent parallelism in photonics to enable large-scale programmable convolution kernels and,in turn,greatly reduce the dimensions required by subsequent fully connected layers.Experimental validation achieves high classification accuracies of 96%(86%)on the MNIST(Fashion-MNIST)dataset and 84.6%on the AG News dataset while dramatically reducing the required subsequent fully connected layer dimensions to 196×10(from 784×10)and 175×4(from 800×4),respectively.Furthermore,our devices can be driven by commercial field-programmable gate array systems;a unique advantage in addition to their scalable channel number and kernel size.Our architecture provides a solution to build practical machine learning photonic devices.
基金supported by the National Natural Science Foundation of China(Grant Nos.12192251,12334014,92480001,12134001,12304418,12274130,12274133,12474378,and 12404378)the National Key R&D Program of China(Grant Nos.2022YFA1404600 and 2022YFA1205100)+2 种基金Shanghai Municipal Science and Technology Major Project(Grant No.2019SHZDZX01)the Innovation Program for Quantum Science and Technology(Grant No.2021ZD0301403)the Engineering Research Center for Nanophotonics&Advanced Instrument,Ministry of Education,East China Normal University(Grant No.2023nmc005)。
文摘We report the fabrication of an 8-meter-long thin-flm lithium niobate optical true delay line using the photolithography-assisted chemomechanical etching technique,showing a low transmission loss of 0.036 dB/cm in the conventional telecom band.
基金supported by the National Natural Science Foundation of China(Grant Nos.12192251,12334014,12404378,92480001,12134001,12174113,12174107,12474325,12404379,and 12474378)the Innovation Program for Quantum Science and Technology(Grant No.2021ZD0301403)+1 种基金Shanghai Municipal Science and Technology Major Project(Grant No.2019SHZDZX01)Fundamental Research Funds for the Central Universities,the Engineering Research Center for Nanophotonics&Advanced Instrument,Ministry of Education,East China Normal University(Grant No.2023nmc005).
文摘We present a compact optical delay line(ODL)with wide-range continuous tunability on thin-film lithium niobate platform.The proposed device integrates an unbalanced Mach-Zehnder interferometer(MZI)architecture with dual tunable couplers,where each coupler comprises two 2×2 multimode interferometers and a MZI phase-tuning section.Experimental results demonstrate continuous delay tuning from 0 to 293 ps through synchronized control of coupling coefficients,corresponding to a 4 cm path difference between interferometer arms.The measured delay range exhibits excellent agreement with theoretical predictions derived from ODL waveguide parameters.This result addresses critical challenges in integrated photonic systems that require precise temporal control,particularly for applications in optical communications and quantum information processing,where a wide tuning range is paramount.
