检索结果-内蒙古大学图书馆

conference on Lasers and Electro-Optics Europe (CLEO EUROPE)

作者： Kilian Müller Julien Launay Iacopo Poli Matthew Filipovich Alessandro Capelli Daniel Hesslow Igor Carron Laurent Daudet Florent Krzakala Sylvain Gigan LightOn Paris France École Polytechnique Fédérale de Lausanne (EPFL) Information Learning and Physics lab. Lausanne Switzerland Laboratoire Kastler Brossel ENS-Universite PSL CNRS Sorbonne Universite College de France Paris France

ISBN: (纸本)9798350345995

Artificial Neural Networks (ANN) are habitually trained via the back-propagation (BP) algorithm. This approach has been extremely successful: Current models like GPT-3 have O(10 11 ) parameters, are trained on O(10 11 ) words and produce awe-inspiring results. However, there are good reasons to look for alternative training methods: With current algorithms and hardware constraints sometimes only half the available computing power is actually used. This is due to a complicated interplay between the size of the ANN, the available memory, throughput limitations of interconnects, the architecture of the network of computers, and the training algorithm. Training a model like the aforementioned GPT-3 takes months and costs millions. A different training paradigm, which could make clever use of specialized hardware, may train large ANNs more efficiently.

关键词： Neural networks optical neural systems optical signal processing devices

来源：评论

学校读者我要写书评

暂无评论

The information Bottleneck Method in Deep Learning: Principles, Applications and Challenges

The Information Bottleneck Method in Deep Learning: Principl...

引用

IEEE International conference on Signal processing, information, Communication & systems (SPICSCON)

作者： Md Nurul Absar Siddiky Rashadul Hasan Badhon Muhammad Enayetur Rahman M M Salman Md Soyaib Hossain Sohag Dept. of ECE UNC at Charlotte Charlotte NC USA Dept. of ECE Old Dominion University Norfolk VA USA Dept. of ECE Khulna University Khulna Bangladesh Dept. of Physics and Optical Science UNC at Charlotte Charlotte NC USA

ISBN: (数字)9798331510213

ISBN: (纸本)9798331510220

The information Bottleneck (IB) method provides a theoretical framework for balancing complexity and accuracy in machine learning models by compressing input data while retaining relevant information. This paper presents a compre-hensive review of the applications of the IB method in deep learning, focusing on its ability to enhance learning efficiency, generalization, and adversarial robustness. Variations like the Variational information Bottleneck (VIB) are also explored for their success in improving neural network performance. Notably, the VIB method performed superior on the MNIST dataset, outperforming conventional regularization techniques such as dropout and confidence penalty. In addition to achieving better generalization, the VIB model demonstrates greater resilience to adversarial attacks, requiring more substantial input mod-ifications to mislead the model. However, significant challenges remain, including optimization complexities and scalability issues in large data sets. This paper also identifies future research di-rections that aim to address these limitations, such as developing more scalable IB algorithms and enhancing adversarial defense mechanisms, to fully realize the potential of IB-based learning models.

关键词： Deep learning Reviews Estimation Computer architecture Robustness Data models Complexity theory Optimization Mutual information Resilience

来源：评论

学校读者我要写书评

暂无评论

Photonics-Assisted Frequency Modulated Continuous Wave Harmonic Radar System

Photonics-Assisted Frequency Modulated Continuous Wave Harmo...

引用

Asia Communications and Photonics conference and Exhibition (ACP)

作者： Jie Yang Zhenzhou Tang Yanming Zhang Shilong Pan National Key Laboratory of Microwave Photonics Nanjing University of Aeronautics and Astronautics Nanjing China Future Research Lab China Mobile Research Institute Beijing China

ISBN: (数字)9798350379266

ISBN: (纸本)9798350379273

Unlike traditional electrical harmonic radar systems that rely on frequency-doubling devices to generate frequency-doubled signals, a photonics-assisted frequency modulated continuous wave (FMCW) harmonic radar is proposed and experimentally verified for the first time. A single dual-polarization Mach-Zehnder modulator (DPol-MZM) is employed at the radar transmitter to generate both the fundamental and frequency-doubled signals by setting the different polarization states, and an electrical mixer is used to realize dechirp processing. In the experiment, a 26-GHz frequency-doubled signal with 2 GHz bandwidth is generated, demonstrating a distance measurement error of less than 2 cm when the detection range is 45 cm.

关键词： Time-frequency analysis Frequency modulation Radar Bandwidth Harmonic analysis Distance measurement Radar signal processing Frequency measurement optical transmitters Photonics

来源：评论

学校读者我要写书评

暂无评论

Research on intelligent monitoring system of facility environment based on cloud control

Research on intelligent monitoring system of facility enviro...

引用

Electronics and devices, Computational Science (ICEDCS), International conference on

作者： Shujiao Tian Yue Zhou Yue Zuo Rui Zhang Xiuyuan Peng Institute of Information Liaoning Academy of Agricultural Sciences Shenyang China Food and Processing Research Institute Liaoning Academy of Agricultural Sciences Shenyang China

ISBN: (数字)9798331527624

ISBN: (纸本)9798331527631

With the continuous development of modern agricultural production modes, facility agriculture, as an important component, imposes higher requirements on environmental monitoring and control. This paper focuses on facility environmental monitoring. Through the construction of a comprehensive monitoring index system for facility vegetable production environment, sensor selection and calibration, the formulation of sensor layout scheme, and the research and development of facility environment monitoring equipment, a robust hardware foundation for facility environmental monitoring is established. Additionally, an intelligent monitoring system based on cloud control technology has been introduced, combined with interval control algorithms, aimed at achieving precision control of agricultural facility environments.

关键词： Cloud computing Stability criteria Production Real-time systems Hardware Agriculture Calibration System software Environmental monitoring Indexes

来源：评论

学校读者我要写书评

暂无评论

Enhancing the performance of optical camera communication via accumulative sampling

引用

OPTICS EXPRESS 2021年第12期29卷 19015-19023页

作者： Zhang, Pinpin Wang, Qiuyu Yang, Yanbing Wang, Yunfeng Sun, Yimao Xu, Wenzheng Luo, Jun Chen, Liangyin Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Sichuan Univ Inst Ind Internet Res Chengdu 610065 Peoples R China Nanyang Mchnol Univ Sch Comp Sci & Engn 50 Nanyang Ave Singapore 639798 Singapore

Deemed as a practical approach to realize Visible Light Communication on commercial-off-the-shelf devices, the optical Camera Communication (OCC) is attracting increasing attention, thanks to its readiness to be built purely upon ubiquitous LED illuminating infrastructure and handy smartphones. However, limited by the low sampling ability of the built-in camera on a smartphone, the performance of existing OCC systems is still far away from the requirements of practical applications. To this end, we further investigate the reception ability of the smartphone's camera and propose an accumulative sampling scheme to improve the performance of the OCC system. Essentially, the proposed scheme can use all the grayscale information of the pixels projected by the LED transmitter, whereas the conventional ones normally use single row (or column) pixels for demodulating. By implementing the lightweight demodulation algorithm with accumulative sampling, we experimentally verify its effectiveness for supporting higher transmission frequency hence better performance in terms of data rate. Extensive evaluations have shown the BERs of the proposed method are over 87% and 96% lower than that provided by the baselines at a maximum transmission frequency of 5 kHz for the Samsung S8 and iPhone 8 Plus receivers, respectively. (C) 2021 optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： CMOS cameras Image processing algorithms Machine vision Motion detection optical wireless communication Visible light communications

来源：评论

学校读者我要写书评

暂无评论

Acoustic Howling Suppression with Neural Networks using Real-world Data 24

Acoustic Howling Suppression with Neural Networks using Real...

引用

24th IEEE International conference on High Performance Computing and Communications, 8th IEEE International conference on Data Science and systems, 20th IEEE International conference on Smart City and 8th IEEE International conference on Dependability in Sensor, Cloud and Big Data systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Wan, Liang Lv, Baosheng Liu, Hongqing Gan, Lu Zhou, Yi School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China College of Engineering Design and Physical Science Brunel Univeristy London United Kingdom

ISBN: (纸本)9798350319934

Due to the closed loop between the microphone and loudspeaker, howling occurs in scenarios such as meetings, KTV, and smart classroom. The howling will not only affect the people's hearing, but also damage audio equipment, bringing poor experiences to listeners. The current high-end devices are equipped with howling suppression algorithms, where traditional signal processing methods such as frequency shift, notch filter, and adaptive feedback cancellation are usually adopted. In this work, we attempt to leverage the power of deep learning techniques to perform howling suppression. To that aim, we set up an environment in which the howling sound is generated and recorded. Based on this setting, we totally collected 36 hours data for the purpose of training. To demonstrate the potentials of deep learning, several networks have been experimented and the corresponding results are reported. The results show that the deep learning-based methods produce a superior howling suppression performance, which indicates the feasibility of using deep learning in this task. © 2022 IEEE.

关键词： Notch filters

来源：评论

学校读者我要写书评

暂无评论

Extended field of vision by using two synchronized camera acquisition off-axis holograms

Extended field of vision by using two synchronized camera ac...

引用

International conference on Image and Signal processing and their Applications (ISPA)

作者： Omar Chaab Fatan Bougheziou Malika Mimi Serge Simoëns Department of Sciences and Technology Signals and Systems Laboratory University Abdelhamid Ibn Badis Mostaganem Algeria Applied Optics Laboratory Institute of Optics and Fine Mechanics University Ferhat Abbas Setif Algeria Department of Electrical Engineering Signals and Systems Laboratory University Abdelhamid Ibn Badis Mostaganem Algeria Acoustic and Fluid Mechanics Laboratory UMR CNRS 5509 UCB Lyon I INSA Central School of Lyon Ecully Lyon France

ISBN: (数字)9798350309249

ISBN: (纸本)9798350309256

Digital holography (DH) is an imaging technique that allows the recording and the reconstruction of the complex optical field (complete information) in both amplitude and phase. Its main advantage is the possibility to modify the recorded wavefront to get free-aberration version. This technique represents the best contender for metrological applications especially in mechanical fluids where it gives an additional dimension for the determination of velocity field of different kind of fluid flow. In order to extend the fluid field of investigation, two synchronized cameras CCD and CMOS with different characteristic (pitch and size) are used for recording two views holograms; this task is implemented under Labview interface which also permits to record successive several holograms with a predefined time interval. The holograms are obtained with the help of holographic setup in off-axis configuration of two views (direct and orthogonal). In order to obtain the total field of view, the two reconstructed holograms must have the same output resolution.

关键词： Image resolution Heuristic algorithms Signal processing algorithms Transforms Holography Cameras Synchronization

来源：评论

学校读者我要写书评

暂无评论

RRAM-Based in-Memory Computing for Intelligent Applications

RRAM-Based in-Memory Computing for Intelligent Applications

引用

China Semiconductor Technology International conference (CSTIC)

作者： Zongwei Wang Yujie Chen Lin Bao Qishen Wang Yuhang Yang Shengyu Bao Jingwei Sun Linbo Shan Qilin Zheng Cuimei Wang Yimao Cai Ru Huang School of Integrated Circuits Beijing Advanced Innovation Center for Integrated Circuits Peking University Beijing P. R. China State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications Beijing P. R. China

ISBN: (数字)9798331513351

ISBN: (纸本)9798331513368

The rapid advancement of artificial intelligence has fueled a heightened demand for highly energy-efficient chips. Nevertheless, conventional von Neuman computation architectures encounter critical bandwidth bottlenecks when handling vast amounts of real-time data processing. In-memory computing (IMC) paradigms leveraging resistive random-access memory (RRAM) have demonstrated remarkable potential in enabling these burgeoning intelligent applications. In this paper, we have demonstrated our efforts on RRAM-based IMC systems, encompassing the design of RRAM devices and the implementation of RRAM-based IMC chips. We envision these works may set the stage for future applications in RRAM in-memory computing technology.

关键词： Integrated circuits Image recognition Computer architecture Bandwidth In-memory computing Data processing Real-time systems Energy efficient computing Calibration Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

A Low Cost on-Device Intruder Detection System for Smart Home Environment

A Low Cost on-Device Intruder Detection System for Smart Hom...

引用

conference on information and Communication Technology (CICT)

作者： Chayan Maiti Vivekanand E Sreekumar Muthuswamy Department of Mechanical Engineering Centre for AI IoT and Robotics Indian Institute of Information Technology Design and Manufacturing Kancheepuram Chennai India

ISBN: (数字)9798331531539

ISBN: (纸本)9798331531546

Robust security is tritical for smart homes to protect families and goods from potential intruder threats. Vision-based intruder detection systems are commonly used for this task. However, only a few households have adopted such security technology because of its high cost, which includes both expensive devices and service costs. To address this issue, a low-cost intruder detection system is investigated in this study, leveraging a Raspberry Pi 4 with a camera module. Smart resource utilization strategies are employed to enable on-device local processing for privacy preservation of sensitive video data. To achieve real-time processing on resource constrain hardware, efficient motion detection is accomplished using the frame subtraction technique, while rapid face detection is accomplished through the haar cascade utilizing Kalman filter. Face identification using OpenFace model is speed up by subsequent template matching technique. The proposed algorithm achieved an average frame rate of 22 FPS making it capable for real-time intruder detection with environmental constrain.

关键词： Costs Subtraction techniques Smart homes Prediction algorithms Real-time systems Motion detection Face detection Kalman filters Security Faces

来源：评论

学校读者我要写书评

暂无评论

Edge Device Selection For Industrial IoT Task Offloading In Mobile Edge Computing

Edge Device Selection For Industrial IoT Task Offloading In ...

引用

Omni-layer Intelligent systems (COINS), International conference on

作者： Megha Sharma Abhinav Tomar Abhishek Hazra Zaid Akhter Daksh Dhangar Rahul Kumar Singh Department of Computer Science and Engineering Netaji Subhas University of Technology New Delhi India Department of Computer Science and Engineering Indian Institute of Information Technology Sri City India

ISBN: (数字)9798350349597

ISBN: (纸本)9798350349603

In the realm of Mobile Edge Computing (MEC), mobile devices have the option to transfer their tasks to edge servers for processing, thereby significantly diminishing task completion duration and reducing the energy consumption of mobile devices. This offloading mechanism optimizes resource utilisation and enhances overall efficiency by leveraging the computational capabilities of nearby edge servers. This paper addresses the issue of efficient task offloading from mobile devices to edge servers in resource-constrained Industrial Internet of Things (IIoT) heterogenous networks, focusing on minimising energy consumption and heterogenous network delay. The methodology involves checking the matching feasibility using Hall's Marriage Theorem and employing a server selection algorithm for task assignment. The results show that the proposed approach minimizes energy consumption and overall time delay compared to standard algorithms. The implications include the potential for improving various QoS factors in future research.

关键词： Energy consumption Multi-access edge computing Quality of service Mobile handsets Servers Resource management Task analysis

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：