检索结果-南通市图书馆

Science China(Information Sciences) 2020年第6期63卷 176-183页

作者： Bowen MA weiwen zou State Key Laboratory of Advanced Optical Communication Systems and Networks Intelligent Microwave Lightwave Integration Innovation Center (iMLic) Department of Electronic Engineering Shanghai Jiao Tong University

We find that a commonly-used distributed feedback laser diode(DFB-LD) can work as a gradedpotential-signaling photonic neuron. Through theoretical and experimental demonstration, DFB-LDs are proved useful for three graded-potential-signaling-based neuromorphic processing applications of the pattern recognition, the single-wavelength implementation of spike timing dependent plasticity(STDP), and the sound azimuth measurement. The pattern recognition with a full-width-at-half-maximum(FWHM) of 1 μs is realized in the experiment.

关键词： neuromorphic photonics graded-potential-signaling photonic neuron pattern recognition optical spike timing dependent plasticity sound azimuth measurement

Towards an intelligent photonic system

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第6期63卷 80-96页

作者： weiwen zou Bowen MA Shaofu XU Xiuting zou Xingjun WANG State Key Laboratory of Advanced Optical Communication Systems and Networks Intelligent Microwave Lightwave Integration Innovation Center (iMLic) Department of Electronic EngineeringShanghai Jiao Tong University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Engineering and Computer Science Peking University

The emerging intelligence technologies represented by deep learning have broadened their applications to various fields. Beyond the conventional electronics-based processing systems, the convergence of photonics and artificial intelligence(AI) technology enhances the performance and learning ability of AI. In this review, we propose the concept of an intelligent photonic system(IPS), illustrating it as a developing architecture with three different versions. For each version of IPS, we review several representative *** we discuss the challenges towards an IPS and provide some prospects for the future development.

关键词： intelligent photonic system deep learning artificial intelligence optical neural network neuromorphic photonics

Towards silicon photonic neural networks for artificial intelligence

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第6期63卷 105-118页

作者： Bowen BAI Haowen SHU Xingjun WANG weiwen zou State Key Laboratory of Advanced Optical Communications System and Networks School of Electronics Engineering and Computer Science Peking University Frontiers Science Center for Nano-optoelectronics Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks Intelligent Microwave Lightwave Integration Innovation Center(iMLic) Department of Electronic Engineering Shanghai Jiao Tong University

Brain-inspired photonic neural networks for artificial intelligence have attracted renewed interest. For many computational tasks, such as image recognition, speech processing and deep learning, photonic neural networks have the potential to increase the computing speed and energy efficiency on the orders of magnitude compared with digital electronics. Silicon Photonics, which combines the advantages of electronics and photonics, brings hope for the large-scale photonic neural network integration. This paper walks through the basic concept of artificial neural networks and focuses on the key devices which construct the silicon photonic neuromorphic systems. We review some recent important progress in silicon photonic neural networks, which include multilayer artificial neural networks and brain-like neuromorphic systems, for artificial intelligence. A prototype of silicon photonic artificial intelligence processor for ultra-fast neural network computing is also proposed. We hope this paper gives a detailed overview and a deeper understanding of this emerging field.

关键词： photonic neural networks artificial intelligence deep learning photonic computing accelerator silicon photonics

Deep-learning-powered photonic analogto-digital conversion

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Light(Science & Applications) 2019年第1期8卷 611-621页

作者： Shaofu Xu Xiuting zou Bowen Ma Jianping Chen Lei Yu weiwen zou State Key Laboratory of Advanced Optical Communication Systems and Networks Intelligent Microwave Lightwave Integration Innovation Center(iMLic)Department of Electronic EngineeringShanghai Jiao Tong University200240 ShanghaiChina

Analog-to-digital converters(ADCs)must be high speed,broadband,and accurate for the development of modern information systems,such as radar,imaging,and communications systems;photonic technologies are regarded as promising technologies for realizing these advanced ***,we present a deep-learning-powered photonic ADC architecture that simultaneously exploits the advantages of electronics and photonics and overcomes the bottlenecks of the two technologies,thereby overcoming the ADC tradeoff among speed,bandwidth,and *** supervised training,the adopted deep neural networks learn the patterns of photonic system defects and recover the distorted data,thereby maintaining the high quality of the electronic quantized data succinctly and *** numerical and experimental results demonstrate that the proposed architecture outperforms state-ofthe-art ADCs with developable high throughput;hence,deep learning performs well in photonic ADC *** anticipate that the proposed architecture will inspire future high-performance photonic ADC design and provide opportunities for substantial performance enhancement for the next-generation information systems.

关键词： thereby Deep overcome

Analog spatiotemporal feature extraction for cognitive radio-frequency sensing with integrated photonics

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Light(Science & Applications) 2024年第3期13卷 478-487页

作者： Shaofu Xu Binshuo Liu Sicheng Yi Jing Wang weiwen zou State Key Laboratory of Advanced Optical Communication Systems and Networks Intelligent Microwave Lightwave Integration Innovation Center(imLic)Department of Electronic EngineeringShanghai Jiao Tong UniversityShanghaiChina

Analog feature extraction(AFE)is an appealing strategy for low-latency and efficient cognitive sensing systems since key features are much sparser than the Nyquist-sampled ***,applying AFE to broadband radio-frequency(RF)scenarios is challenging due to the bandwidth and programmability bottlenecks of analog electronic ***,we introduce a photonics-based scheme that extracts spatiotemporal features from broadband RF signals in the analog *** feature extractor structure inspired by convolutional neural networks is implemented on integrated photonic circuits to process RF signals from multiple antennas,extracting valid features from both temporal and spatial *** of the tunability of the photonic devices,the photonic spatiotemporal feature extractor is trainable,which enhances the validity of the extracted ***,a digital-analog-hybrid transfer learning method is proposed for the effective and low-cost training of the photonic feature *** validate our scheme,we demonstrate a radar target recognition task with a 4-GHz instantaneous *** results indicate that the photonic analog feature extractor tackles broadband RF signals and reduces the sampling rate of analog-to-digital converters to 1/4 of the Nyquist sampling while maintaining a high target recognition accuracy of 97.5%.Our scheme offers a promising path for exploiting the AFE strategy in the realm of cognitive RF sensing,with the potential to contribute to the efficient signal processing involved in applications such as autonomous driving,robotics,and smart factories.

关键词： scheme driving smart

Distributed Discrimination of Strain and Temperature Based on Brillouin Dynamic Grating in an Optical Fiber

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Photonic Sensors 2013年第4期3卷 332-344页

作者： Kazuo HOTATE weiwen zou Rodrigo Kendy YAMASHITA Zuyuan HE Department of Electrical Engineering and Information Systems The University of Tokyo Japan State Key Laboratory Advanced Optical Communication Systems and Networks Department of Electronic EngineeringShanghai Jiao Tong University China

This paper reviews distributed discrimination of strain and temperature by use of an optical fiber based on fiber optic nerve systems. The preliminary method based on multiple resonance peaks of the Brillouin gain spectrum in a specially-designed fiber is firstly introduced. The complete discrimination of strain and temperature based on the Brillouin dynamic grating in a polarization maintaining fiber is extensively presented. The basic principle and two experimental schemes of distributed discrimination based on fiber optic nerve systems are demonstrated. The performance of the high discriminative accuracy （0.1 ~C-0.3 ~C and 5 kte-12~te） and high spatial resolution （-10 cm） with the effective measurement points of about 50 for a standard system configuration or about 1000 for a modified one will be highly expected in real industry applications.

关键词： Fiber optic nerve systems Brillouin optical correlation-domain analysis Brillouin dynamic grating distributed discrimination strain temperature

Comb-based photonic neural population for parallel and nonlinear processing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Photonics Research 2022年第1期10卷 174-182页

作者： BOWEN MA JUNFENG ZHANG weiwen zou State Key Laboratory of Advanced Optical Communication Systems and Networks Intelligent Microwave Lightwave Integration Innovation Center(imLic)Department of Electronic EngineeringShanghai Jiao Tong UniversityShanghai 200240China

It is believed that neural information representation and processing relies on the neural population instead of a single *** neuromorphic photonics,photonic neurons in the form of nonlinear responses have been extensively studied in single devices and temporal ***,to construct a photonic neural population(PNP),the process of scaling up and massive interconnections remain challenging considering the physical complexity and response ***,we propose a comb-based PNP interconnected by carrier coupling with superior *** unique properties of neural population are theoretically and experimentally demonstrated in the comb-based PNP,including nonlinear response curves and population activities coding.A classification task of three input patterns with dual radio-frequency(RF) tones is successfully implemented in a time-efficient manner,which allows the comb-based PNP to make effective use of the ultra-broad bandwidth of photonics for parallel and nonlinear processing.

关键词： nonlinear scaling neural

维普期刊数据库

Optical coherent dot-product chip for sophisticated deep learning regression

在线全文

学校读者我要写书评

暂无评论

Light(Science & Applications) 2021年第12期10卷 2330-2341页

作者： Shaofu Xu Jing Wang Haowen Shu Zhike Zhang Sicheng Yi Bowen Bai Xingjun Wang Jianguo Liu weiwen zou State Key Laboratory of Advanced Optical Communication Systems and Networks Intelligent Microwave Lightwave Integration Innovation Center(imLic)Department of Electronic EngineeringShanghai Jiao Tong University800 Dongchuan RoadShanghai 200240China State Key Laboratory of Advanced Optical Communications System and Networks Department of ElectronicsSchool of Electronics Engineering and Computer SciencePeking UniversityBeijing 100871China Institution of Semiconductors Chinese Academy of SciencesBeijing 100083China

Optical implementations of neural networks(ONNs)herald the next-generation high-speed and energy-efficient deep learning computing by harnessing the technical advantages of large bandwidth and high parallelism of ***,due to the problems of the incomplete numerical domain,limited hardware scale,or inadequate numerical accuracy,the majority of existing ONNs were studied for basic classification *** that regression is a fundamental form of deep learning and accounts for a large part of current artificial intelligence applications,it is necessary to master deep learning regression for further development and deployment of ***,we demonstrate a silicon-based optical coherent dot-product chip(OCDC)capable of completing deep learning regression *** OCDC adopts optical fields to carry out operations in the complete real-value domain instead of in only the positive *** reusing,a single chip conducts matrix multiplications and convolutions in neural networks of any ***,hardware deviations are compensated via in-situ backpropagation control provided the simplicity of chip ***,the OCDC meets the requirements for sophisticated regression tasks and we successfully demonstrate a representative neural network,the AUTOMAP(a cutting-edge neural network model for image reconstruction).The quality of reconstructed images by the OCDC and a 32-bit digital computer is *** the best of our knowledge,there is no precedent of performing such state-of-the-art regression tasks on ONN *** is anticipated that the OCDC can promote the novel accomplishment of ONNs in modern AI applications including autonomous driving,natural language processing,and scientific study.

关键词： neural hardware coherent

Optical tensor core architecture for neural network training based on dual-layer waveguide topology and homodyne detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Optics Letters 2021年第8期19卷 84-89页

作者： Shaofu Xu weiwen zou Department of Electronic EngineeringShanghai Jiao Tong UniversityShanghai 200240China

We propose an optical tensor core(OTC) architecture for neural network training. The key computational components of the OTC are the arrayed optical dot-product units(DPUs). The homodyne-detection-based DPUs can conduct the essential computational work of neural network training, i.e., matrix-matrix multiplication. Dual-layer waveguide topology is adopted to feed data into these DPUs with ultra-low insertion loss and cross talk. Therefore, the OTC architecture allows a large-scale dot-product array and can be integrated into a photonic chip. The feasibility of the OTC and its effectiveness on neural network training are verified with numerical simulations.

关键词： optical tensor core neural network training matrix multiplication homodyne detection dual-layer waveguides

维普期刊数据库

Fully integrated hybrid microwave photonic receiver

在线全文

学校读者我要写书评

暂无评论

Photonics Research 2022年第6期10卷 1472-1483页

作者： JIACHEN LI SIGANG YANG HONGWEI CHEN XINGJUN WANG MINGHUA CHEN weiwen zou Beijing National Research Center for Information Science and Technology(BNRist) Department of Electronic EngineeringTsinghua UniversityBeijing 100084China State Key Laboratory of Advanced Optical Communications System and Networks Department of ElectronicsSchool of Electronics Engineering and Computer SciencePeking UniversityBeijing 100871China State Key Laboratory of Advanced Optical Communication Systems and Networks Intelligent Microwave Lightwave Integration Innovation Center(imLic)Department of Electronic EngineeringShanghai Jiao Tong UniversityShanghai 200240China

Microwave photonic receivers are a promising candidate in breaking the bandwidth limitation of traditional radio-frequency(RF)*** further balance the performance superiority with the requirements regarding size,weight,and power consumption(SWa P),the implementation of integrated microwave photonic microsystems has been considered an upgrade ***,up to now,to the best of our knowledge,chip-scale fully integrated microwave photonic receivers have not been reported due to the limitation of material *** this paper,we report a fully integrated hybrid microwave photonic receiver(FIH-MWPR)obtained by comprising the indium phosphide(In P)laser chip and the monolithic silicon-on-insulator(SOI)photonic circuit into the same substrate based on the low-coupling-loss micro-optics *** from the integration of all optoelectronic components,the packaged FIH-MWPR exhibits a compact volume of 6 cmand low power consumption of 1.2 *** FIH-MWPR supports a wide operation bandwidth from 2 to 18 ***,its RF-link performance to down-convert the RF signals to the intermediate frequency is experimentally characterized by measuring the link gain,the noise figure,and the spurious-free dynamic range metrics across the whole operation frequency ***,we have utilized it as a de-chirp receiver to process the broadband linear frequencymodulated(LFM)radar echo signals at different frequency bands(S-,C-,X-,and Ku-bands)and successfully demonstrated its high-resolution-ranging *** the best of our knowledge,this is the first realization of a chip-scale broadband fully integrated microwave photonic receiver,which is expected to be an important step in demonstrating the feasibility of all-integrated microwave photonic microsystems oriented to miniaturized application scenarios.

关键词： method microwave bands

维普期刊数据库