检索结果-内蒙古大学图书馆

Hardware-algorithm collaborative computing with photonic spiking neuron chip based on an integrated Fabry-Perot laser with a saturable absorber

引用

OPTICA 2023年第2期10卷 162-171页

作者： Xiang, Shuiying Shi, Yuechun Guo, Xingxing Zhang, Yahui Wang, Hongji Zheng, Dianzhuang Song, Ziwei Han, Yanan Gao, Shuang Zhao, Shihao Gu, Biling Wang, Hailing Zhu, Xiaojun Hou, Lianping Chen, Xiangfei Zheng, Wanhua Ma, Xiaohua Hao, Yue Xidian Univ State Key Lab Integrated Serv Networks State Key Discipline Lab Wide Bandgap Semicond Tec Xian 710071 Peoples R China Yongjiang Lab 1792 Cihai South Rd Ningbo 315202 Peoples R China Nanjing Univ Inst Opt Commun Engn Coll Engn & Appl Sci Key Lab Intelligent Opt Sensing & ManipulatNatl L Nanjing 210023 Peoples R China Chinese Acad Sci Inst Semicond Lab Solid State Optoelect Informat Technol Beijing 100083 Peoples R China Nantong Univ Sch Informat Sci & Technol Nantong 226019 Jiangsu Peoples R China Univ Glasgow James Watt Sch Engn Glasgow City G12 8QQ Scotland

Photonic neuromorphic computing has emerged as a promising approach to building a low-latency and energy-efficient non-von Neuman computing system. A photonic spiking neural network (PSNN) exploits brain-like spatiotemporal processing to realize high-performance neuromorphic computing. However, the nonlinear computation of a PSNN remains a significant challenge. Here, we propose and fabricate a photonic spiking neuron chip based on an integrated Fabry-Perot laser with a saturable absorber (FP-SA). The nonlinear neuron-like dynamics including temporal integration, threshold and spike generation, a refractory period, inhibitory behavior and cascadability are experimentally demonstrated, which offers an indispensable fundamental building block to construct the PSNN hardware. Furthermore, we propose time-multiplexed temporal spike encoding to realize a functional PSNN far beyond the hardware integration scale limit. PSNNs with single/cascaded photonic spiking neurons are experimentally demonstrated to realize hardware-algorithm collaborative computing, showing the capability to perform classification tasks with a supervised learning algorithm, which paves the way for a multilayer PSNN that can handle complex tasks. (c) 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Distributed feedback lasers neural networks optical networks optical neural systems Saturable absorbers Variable optical attenuators

来源：评论

学校读者我要写书评

暂无评论

Handling Overfitting and Imbalance Data in Modelling Convolutional neural networks for Astronomical Transient Discovery

Handling Overfitting and Imbalance Data in Modelling Convolu...

引用

2024 International Conference on computing, Communication, Cybersecurity and AI

作者： Boongoen, Tossapon Iam-On, Natthakan Aberystwyth Univ Dept Comp Sci Adv Reasoning Res Grp Aberystwyth Ceredigion Wales

ISBN: (纸本)9783031744426;9783031744433

Given development in telescope and image acquisition technology, efficient processing and timely discovery of events have become challenges for astronomers and data scientists around the globe. Among modern sky survey projects, GOTO (Gravitational-wave optical Transient Observer) is searching for transient events with new breed of optical survey telescopes, which allow a faster and deeper assessment. As compared to conventional machine learning techniques that have been sup-optimal to identify new sources from a large pool of candidates, this works presents the application of convolutional neural networks, with different data augmentation methods being explored to handle issues of overfitting and imbalance data.

关键词： Astronomy Transient event Classification CNN Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Deep learning adversarial attacks and defenses on license plate recognition system

引用

CLUSTER computing-THE JOURNAL OF networks SOFTWARE TOOLS AND APPLICATIONS 2024年第8期27卷 11627-11644页

作者： Vizcarra, Conrado Alhamed, Shadan Algosaibi, Abdulelah Alnaeem, Mohammed Aldalbahi, Adel Aljaafari, Nura Sawalmeh, Ahmad Nazzal, Mahmoud Khreishah, Abdallah Alhumam, Abdulaziz Anan, Muhammad King Faisal Univ Dept Comp Sci CCSIT Al Hasa 31982 Saudi Arabia Prince Sattam bin Abdulaziz Univ Appl Coll AlKharj Saudi Arabia King Faisal Univ Dept Comp Networks & Commun CCSIT Al Hasa 31982 Saudi Arabia King Faisal Univ Dept Elect Engn POB 380 Al Hufof 31982 Al Hassa Saudi Arabia Alfaisal Univ Software Engn Dept POB 50927 Riyadh 11533 Saudi Arabia New Jersey Inst Technol Newark NJ 07102 USA

The breakthroughs in Machine learning and deep neural networks have revolutionized the handling of critical practical challenges, achieving state-of-the-art performance in various computer vision tasks. Notably, the application of deep neural networks in optical character recognition (OCR) has significantly enhanced the performance of OCR systems, making them a pivotal preprocessing component in text analysis pipelines for crucial applications such as license plate recognition (LPR) systems, where the efficiency of OCR is paramount. However, despite the advancements, the integration of deep neural networks in OCR introduces inherent security vulnerabilities, particularly susceptibility to adversarial examples. Adversarial examples in LPR systems are crafted by introducing perturbations to original license plate images, which can effectively compromise the integrity of the license plate recognition process, leading to erroneous license plate number identification. Given that the primary goal of OCR in this context is to accurately recognize license plate numbers, even a single misinterpreted character can significantly impact the overall performance of the LPR system. The vulnerability of LPR systems to adversarial attacks underscores the urgent need to address the security weaknesses inherited from deep neural networks. In response to these challenges, the exploration of alternative defense mechanisms, such as image denoising and in-painting, presents a compelling approach to bolstering the resilience of LPR systems against adversarial attacks. By prioritizing practical implementation and integration of image denoising and inpainting techniques align with the operational requirements of real-world LPR systems. These methods can be seamlessly integrated into existing pipelines, offering pragmatic and accessible means of enhancing security without imposing significant computational overhead. By embracing a multi-faceted approach that combines the strengths of traditio

关键词： Adversarial attack Adversarial defense License plate recognition system optical character recognition

来源：评论

学校读者我要写书评

暂无评论

A Reconfigurable Linear RF Analog Processor for Realizing Microwave Artificial neural Network

引用

IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES 2024年第2期72卷 1290-1301页

作者： Zhu, Minning Kuo, Tzu-Wei Wu, Chung-Tse Michael Rutgers State Univ Dept Elect & Comp Engn New Brunswick NJ 08854 USA Univ Michigan Dept Cell & Dev Biol Med Sch Ann Arbor MI 48109 USA

Owing to the data explosion and rapid development of artificial intelligence (AI), particularly deep neural networks (DNNs), the ever-increasing demand for large-scale matrix-vector multiplication has become one of the major issues in machine learning (ML). Training and evaluating such neural networks rely on heavy computational resources, resulting in significant system latency and power consumption. To overcome these issues, analog computing using optical interferometric-based linear processors have recently appeared as promising candidates in accelerating matrix-vector multiplication and lowering power consumption. On the other hand, radio frequency (RF) electromagnetic waves can also exhibit similar advantages as the optical counterpart by performing analog computation at light speed with lower power. Furthermore, RF devices have extra benefits such as lower cost, mature fabrication, and analog-digital mixed design simplicity, which has great potential in realizing affordable, scalable, low latency, low power, near-sensor radio frequency neural network (RFNN) that may greatly enrich RF signal processing capability. In this work, we propose a 2X2 reconfigurable linear RF analog processor in theory and experiment, which can be applied as a matrix multiplier in an artificial neural network (ANN). The proposed device can be utilized to realize a 2X2 simple RFNN for data classification. An 8X8 linear analog processor formed by 28 RFNN devices are also applied in a 4-layer ANN for Modified National Institute of Standards and Technology (MNIST) dataset classification.

关键词： Analog signal processing artificial intelligence (AI) machine learning (ML) radio frequency (RF) analog processor RF neural network (RFNN)

来源：评论

学校读者我要写书评

暂无评论

Fast square-oscillations in semiconductor VCSELs with delayed orthogonal polarization feedback

引用

OPTICS EXPRESS 2025年第9期33卷 18601-18610页

作者： Wang, Tao Tu, Zhicong Ma, Yixing Li, Yiheng Li, Zhibo Qin, Fan Barland, Stephane Xiang, Shuiying Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Univ Cote Azur CNRS UMR 7010 Inst Phys Nice F-06200 Nice France

We present an experimental investigation into the generation of self-sustained and fast square oscillations from the TE mode of semiconductor VCSELs with delayed orthogonal polarization feedback. We find that the low-frequency switching originates from the rotation of the TE and TM modes facilitated by a long time delay, but the fast oscillations are anchored to the frequency beating between the TE and TM modes and are modified by a half-wavelength (lambda/2) plate. A comprehensive analysis of the evolution of the nonlinear dynamics is conducted and the related mechanism is discussed. Our study not only deepens our comprehension of laser nonlinear dynamics but also offers an all-optical approach for producing specialized signals, which could be instrumental in applications such as optical communications and photonic computing leveraging the complexity of long-delay systems.

关键词： Multiplexing neural networks optical computing Quantum computation Semiconductor lasers Vertical cavity surface emitting lasers

来源：评论

学校读者我要写书评

暂无评论

Deep photonic reservoir computer based on frequency multiplexing with fully analog connection between layers

引用

OPTICA 2023年第11期10卷 1478-1485页

作者： Lupo, Alessandro Picco, Enrico Zajnulina, Marina Massar, Serge Univ libre Bruxelles ULB Lab Informat Quant CP224 Av FD Roosevelt 50 B-1050 Brussels Belgium Multitel Innovat Ctr Rue Pierre & Marie Curie 2 B-7000 Mons Belgium

Reservoir computers (RCs) are randomized recurrent neural networks well adapted to process time series, performing tasks such as nonlinear distortion compensation or prediction of chaotic dynamics. Deep reservoir computers (deep-RCs), in which the output of one reservoir is used as the input for another one, can lead to improved performance because, as in other deep artificial neural networks, the successive layers represent the data in more and more abstract ways. We present a fiber-based photonic implementation of a two-layer deep-RC based on frequency multiplexing. The two RC layers are encoded in two frequency combs propagating in the same experimental setup. The connection between the layers is fully analog and does not require any digital processing. We find that the deep-RC outperforms a traditional RC by up to two orders of magnitude on two benchmark tasks. This work paves the way towards using fully analog photonic neuromorphic computing for complex processing of time series, while avoiding costly analog-to-digital and digital-to-analog conversions. (c) 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Analog to digital converters Free space optics Frequency combs neural networks optical components optical computing

来源：评论

学校读者我要写书评

暂无评论

On-Demand Reconfigurable Incoherent optical Matrix Operator for Real-Time Video Image Display

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2023年第6期41卷 1637-1648页

作者： Meng, Xiangyan Shi, Nuannuan Li, Guangyi Zhang, Guojie Li, Wei Zhu, Ninghua Li, Ming Chinese Acad Sci Inst Semicond State Key Lab Integrated Optoelect Beijing 100083 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China Univ Chinese Acad Sci Ctr Mat Sci & Optoelect Engn Beijing 100190 Peoples R China

For emerging application fields such as autonomous driving and computing vision, which demands the real-time response of massive information, advanced image processing techniques on artificial neural networks (ANNs) are crucial. However, with increasing task complexity, the electrical hardware limited by the well-known von Neumann bottleneck is inadequate to meet these extreme requirements in computing speed and computing power. We propose an incoherent optical matrix operator by dynamically manipulating the parameters of the lightwave in terms of the wavelength, time and space to implement the on-demand reconfiguration both in the optical perceptron and optical convolutional processor. For the optical perceptron, it is conducted to perform the case-sensitive classification of 52 English letters. Furthermore, by adjusting the spectral characteristics and output ports, an optical convolution processor is constructed to realize multitask convolution processing for both the image and real-time video. Based on multikernels parallel computing in an optical convolutional layer coupled with an electrically fully connected layer, a convolutional neural network is built to recognize '0-9' handwritten digital images from the Modified National Institute of Standards and Technology (MNIST) database. Owing to the excellent performance of the incoherent beam in terms of the spectral purity, wavelength stability and side-mode suppression ratio, the experimental classification accuracy up to 96.01% greatly matches the theoretical value of 96.67%. Moreover, incoherent information processing is synchronous with data transmission, which releases the requirement of the global clock in digital counterparts. The high-fidelity incoherent convolution processor offers a novel computing framework that serves the next-generation ANN platform.

关键词： optical imaging optical fibers Convolution Kernel optical fiber sensors optical network units optical computing Incoherent optical matrix operator optical convolutional processor optical perceptron

来源：评论

学校读者我要写书评

暂无评论

Implementing optical Analog computing and Electrooptic Hopfield Network by Silicon Photonic Circuits

引用

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES 2024年第5期E107A卷 700-708页

作者： Cong, Guangwei Yamamoto, Noritsugu Inoue, Takashi Maegami, Yuriko Ohno, Morifumi Kita, Shota Kou, Rai Namiki, Shu Yamada, Koji AIST Tsukuba 3058569 Japan AIST Natl Inst Adv Ind Sci & Technol Tsukuba 3058569 Japan AIST Platform Photon Res Ctr Tsukuba 3058569 Japan AIST Microsyst Integrat Labs Tsukuba 3058569 Japan Nippon Telegraph & Tel Corp NTT Basic Res Labs Photon Nanostruct Res Grp Nanophoton Ctr Atsugi 2430198 Japan

Wide deployment of artificial intelligence (AI) is inducing exponentially growing energy consumption. Traditional digital platforms are becoming di ffi cult to fulfill such ever-growing demands on energy efficiency as well as computing latency, which necessitates the development of high e ffi ciency analog hardware platforms for AI. Recently, optical and electrooptic hybrid computing is reactivated as a promising analog hardware alternative because it can accelerate the information processing in an energy -e ffi cient way. Integrated photonic circuits o ff er such an analog hardware solution for implementing photonic AI and machine learning. For this purpose, we proposed a photonic analog of support vector machine and experimentally demonstrated low -latency and low -energy classification computing, which evidences the latency and energy advantages of optical analog computing over traditional digital computing. We also proposed an electrooptic Hopfield network for classifying and recognizing time -series data. This paper will review our work on implementing classification computing and Hopfield network by leveraging silicon photonic circuits.

关键词： photonic neural networks support vector machine integrated photonic circuits silicon photonics machine learning optical AI

来源：评论

学校读者我要写书评

暂无评论

Variational Methods in optical Quantum Machine Learning

引用

IEEE ACCESS 2023年 11卷 131394-131408页

作者： Simonetti, Marco Perri, Damiano Gervasi, Osvaldo Univ Florence Dept Math & Comp Sci I-50134 Florence Italy Univ Perugia Dept Math & Comp Sci I-06123 Perugia Italy

The computing world is rapidly evolving and advancing, with new ground-breaking technologies emerging. Quantum computing and Quantum Machine Learning have opened up new possibilities, providing unprecedented computational power and problem-solving capabilities while offering a deeper understanding of complex systems. Our research proposes new variational methods based on a deep learning system based on an optical quantum neural network applied to Machine Learning models for point classification. As a case study, we considered the binary classification of points belonging to a certain geometric pattern (the Two-Moons Classification problem) on a plane. We think it is reasonable to expect benefits from using hybrid deep learning systems (classical + quantum), not just in terms of accelerating computation but also in understanding the underlying phenomena and mechanisms. This will result in the development of new machine-learning paradigms and a significant advancement in the field of quantum computation. The selected dataset is a set of 2D points creating two interleaved semicircles and is based on a 2D binary classification generator, which aids in evaluating the performance of particular methods. The two coordinates of each unique point, x(1) and x(2), serve as the features since they present two disparate data sets in a two-dimensional representation space. The goal was to create a quantum deep neural network that could recognise and categorise points accurately with the fewest trainable parameters possible.

关键词： Quantum computing variational methods deep learning quantum feed-forward neural networks optical quantum computing

来源：评论

学校读者我要写书评

暂无评论

Real-time localization and classification of the fast-moving target based on complementary single-pixel detection

引用

OPTICS EXPRESS 2025年第5期33卷 11301-11316页

作者： Yang, Jianing Liu, Xinyuan Zhang, Lingyun Zhang, Li Yan, Tingkai Fu, Sheng Sun, Ting Zhan, Haiyang Xing, Fei You, Zheng Tsinghua Univ Dept Precis Instrument Beijing 100084 Peoples R China Tsinghua Univ State Key Lab Precis Measurement Technol & Instrum Beijing 100084 Peoples R China Tsinghua Univ Beijing Adv Innovat Ctr Integrated Circuits Beijing 100084 Peoples R China Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Peoples R China Beijing Informat Sci & Technol Univ Sch Instrument Sci & Optoelect Engn Beijing 100016 Peoples R China

Real-time localization and classification of fast-moving objects are crucial in various applications. Traditional imaging approaches face significant challenges, including large data requirements, limited update rates, motion blur, and restrictions in non-visible wavelengths. This paper proposes an image-free method based on complementary single-pixel detection and centralized geometric moments, which effectively integrates target localization and classification into a unified framework. By employing only four specific illumination patterns, the method can simultaneously determine the centroid position and shape of the target at an update rate of up to 5.55 kHz. Theoretical simulations verify the robustness of the proposed method under similarity transformations. Experimental results indicate that the proposed system achieves accurate real-time target localization and classification under diverse conditions, with an RMSE for centroid localization below 0.5 pixels and 93.3% classification accuracy for 30 different objects. The proposed method demonstrates strong adaptability to complicated environments. It holds significant potential for applications in target tracking, character recognition, industrial automation, and the development of optoelectronic neural networks for advanced optical computing tasks. (c) 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Diffractive optical elements Imaging systems optical computing optical neural systems Single pixel imaging Spatial light modulators

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：