Feature extraction in the optical domain offers a promising low-latency,high-throughput solution.Optical diffraction-based feature extraction operating under a coherent light source can further achieve parallel output...Feature extraction in the optical domain offers a promising low-latency,high-throughput solution.Optical diffraction-based feature extraction operating under a coherent light source can further achieve parallel outputs with low energy consumption.However,it presents significant challenges for maintaining the coherent input,scaling the operation rates beyond 10 GHz,and ensuring the effective extraction of functional configuration simultaneously.We propose an optical feature extraction engine(OFE^(2)),which is composed of a diffraction operator and a data preparation module,powering high-speed feature extraction for both image and temporal series tasks.This OFE^(2)can achieve a core latency of less than 250.5 ps;in addition,it can reach a throughput of 250 GOPS and an efficiency of 2.06 TOPS/W.Supported by the OFE^(2),a novel feature extraction paradigm is emerging,enabling high-speed,low-latency service access for applications in scene recognition,medical assistance,and digital finance.展开更多
With the aid of the latest fiber optic sensing technology parameters in the cure process of ther- mosetting resin-matrix composite, such as temperature, viscosity,void and residual stress, can be monitored entirely an...With the aid of the latest fiber optic sensing technology parameters in the cure process of ther- mosetting resin-matrix composite, such as temperature, viscosity,void and residual stress, can be monitored entirely and efficiently.In this paper, experiment results of viscosity measurement in composite cure process in autoclave using fiber optic sensors are presented. Based on the sensed information, a computer program is utilized to control the cure process. With this technology, the cure process becomes more apparent and controllable, which will greatly improve the cured products and reduce the cost.展开更多
An optical phased array(OPA)featuring all-solid-state beam steering is a promising component for light detection and ranging(LiDAR).There exists an increasing demand for panoramic perception and rapid target recogniti...An optical phased array(OPA)featuring all-solid-state beam steering is a promising component for light detection and ranging(LiDAR).There exists an increasing demand for panoramic perception and rapid target recognition in intricate LiDAR applications,such as security systems and self-driving vehicles.However,the majority of existing OPA approaches suffer from limitations in field of view(FOV)and do not explore parallel scanning,thus restricting their potential utility.Here,we combine a two-dimensional(2D)grating with an FOV-synthetization concept to design a silicon-based top-facing OPA for realizing a wide cone-shaped 360°FOV.By utilizing four OPA units sharing the 2D grating as a single emitter,four laser beams are simultaneously emitted upwards and manipulated to scan distinct regions,demonstrating seamless beam steering within the lateral 360°range.Furthermore,a frequency-modulated dissipative Kerr-soliton(DKS)microcomb is applied to the proposed multi-beam OPA,exhibiting its capability in large-scale parallel multi-target coherent detection.The comb lines are spatially dispersed with a 2D grating and separately measure distances and velocities in parallel,significantly enhancing the parallelism.The results showcase a ranging precision of 1 cm and velocimetry errors of less than 0.5 cm/s.This approach provides an alternative solution for LiDAR with an ultra-wide FOV and massively parallel multi-target detection capability.展开更多
As the core component of the transformer model,the attention has been proved as all you need in artificial intelligence field in recent years.However,conventional electronic processors are unable to cope with the expo...As the core component of the transformer model,the attention has been proved as all you need in artificial intelligence field in recent years.However,conventional electronic processors are unable to cope with the exponentially increasing hardware costs and energy consumption of the computing-expensive attention.While the photonic neural network(NN)chips provide alternative energy-efficient solutions for accelerating the matrix multiplication(MM),existing photonic accelerators are primarily designed for weight-static NNs that involve MM between the learned weight matrix and input tensors and thus are inefficient in supporting attention mechanisms that require dynamic input operands.Here we propose an attention mechanism relying solely on the runtime-programable optical-interference.Through theoretical analyses,numerical simulations and experimental validations,we demonstrate the photonic“all-interference”attention with learning capability equivalent to classical self-attention,and implement the photonic transformer chip(PTC).Evaluation shows that the PTC is promising to exceed 200 pera-operations per second(POPS)with 1POPS/mm2 computation density and 0.5 POPS/W power efficiency,much better than prior photonic accelerators,and delivers over 200×energy reduction and 2 to 3 orders of magnitude higher computation capability compared to the electronic counterpart.The photonic transformer with“all-interference”attention proposed in this work highlights the immense potential of photonics to construct its own computing paradigm for general purpose machine learning.展开更多
This feature issue is the second Joint Applied Optics （AO） and Chinese Optics Letters （COL） Feature Issue on digital holography and three-dimensional （3D） imaging. The first installment of such a joint feature i...This feature issue is the second Joint Applied Optics （AO） and Chinese Optics Letters （COL） Feature Issue on digital holography and three-dimensional （3D） imaging. The first installment of such a joint feature issue was in 2011. In the present feature issue, there are a total of 24 papers in AO and 9 papers in COL.展开更多
基金supported by the National Key Research and Development Program of China(Grant No.2024YFE0203600)the National Natural Science Foundation of China(Grant No.62135009).
文摘Feature extraction in the optical domain offers a promising low-latency,high-throughput solution.Optical diffraction-based feature extraction operating under a coherent light source can further achieve parallel outputs with low energy consumption.However,it presents significant challenges for maintaining the coherent input,scaling the operation rates beyond 10 GHz,and ensuring the effective extraction of functional configuration simultaneously.We propose an optical feature extraction engine(OFE^(2)),which is composed of a diffraction operator and a data preparation module,powering high-speed feature extraction for both image and temporal series tasks.This OFE^(2)can achieve a core latency of less than 250.5 ps;in addition,it can reach a throughput of 250 GOPS and an efficiency of 2.06 TOPS/W.Supported by the OFE^(2),a novel feature extraction paradigm is emerging,enabling high-speed,low-latency service access for applications in scene recognition,medical assistance,and digital finance.
文摘With the aid of the latest fiber optic sensing technology parameters in the cure process of ther- mosetting resin-matrix composite, such as temperature, viscosity,void and residual stress, can be monitored entirely and efficiently.In this paper, experiment results of viscosity measurement in composite cure process in autoclave using fiber optic sensors are presented. Based on the sensed information, a computer program is utilized to control the cure process. With this technology, the cure process becomes more apparent and controllable, which will greatly improve the cured products and reduce the cost.
基金National Key Research and Development Program of China(2022YFA1404001)National Natural Science Foundation of China(62135004)Key Research and Development Program of Hubei Province(2021BAA005)。
文摘An optical phased array(OPA)featuring all-solid-state beam steering is a promising component for light detection and ranging(LiDAR).There exists an increasing demand for panoramic perception and rapid target recognition in intricate LiDAR applications,such as security systems and self-driving vehicles.However,the majority of existing OPA approaches suffer from limitations in field of view(FOV)and do not explore parallel scanning,thus restricting their potential utility.Here,we combine a two-dimensional(2D)grating with an FOV-synthetization concept to design a silicon-based top-facing OPA for realizing a wide cone-shaped 360°FOV.By utilizing four OPA units sharing the 2D grating as a single emitter,four laser beams are simultaneously emitted upwards and manipulated to scan distinct regions,demonstrating seamless beam steering within the lateral 360°range.Furthermore,a frequency-modulated dissipative Kerr-soliton(DKS)microcomb is applied to the proposed multi-beam OPA,exhibiting its capability in large-scale parallel multi-target coherent detection.The comb lines are spatially dispersed with a 2D grating and separately measure distances and velocities in parallel,significantly enhancing the parallelism.The results showcase a ranging precision of 1 cm and velocimetry errors of less than 0.5 cm/s.This approach provides an alternative solution for LiDAR with an ultra-wide FOV and massively parallel multi-target detection capability.
基金supported by the National Key Research and Development Program of China(2021YFB2801900,2021YFB2801901,2021YFB2801902,2021YFB2801904)National Natural Science Foundation of China(No.61974177)+1 种基金National Outstanding Youth Science Fund Project of National Natural Science Foundation of China(62022062)The Fundamental Research Funds for the Central Universities(QTZX23041).
文摘As the core component of the transformer model,the attention has been proved as all you need in artificial intelligence field in recent years.However,conventional electronic processors are unable to cope with the exponentially increasing hardware costs and energy consumption of the computing-expensive attention.While the photonic neural network(NN)chips provide alternative energy-efficient solutions for accelerating the matrix multiplication(MM),existing photonic accelerators are primarily designed for weight-static NNs that involve MM between the learned weight matrix and input tensors and thus are inefficient in supporting attention mechanisms that require dynamic input operands.Here we propose an attention mechanism relying solely on the runtime-programable optical-interference.Through theoretical analyses,numerical simulations and experimental validations,we demonstrate the photonic“all-interference”attention with learning capability equivalent to classical self-attention,and implement the photonic transformer chip(PTC).Evaluation shows that the PTC is promising to exceed 200 pera-operations per second(POPS)with 1POPS/mm2 computation density and 0.5 POPS/W power efficiency,much better than prior photonic accelerators,and delivers over 200×energy reduction and 2 to 3 orders of magnitude higher computation capability compared to the electronic counterpart.The photonic transformer with“all-interference”attention proposed in this work highlights the immense potential of photonics to construct its own computing paradigm for general purpose machine learning.
文摘This feature issue is the second Joint Applied Optics （AO） and Chinese Optics Letters （COL） Feature Issue on digital holography and three-dimensional （3D） imaging. The first installment of such a joint feature issue was in 2011. In the present feature issue, there are a total of 24 papers in AO and 9 papers in COL.
