检索结果-内蒙古大学图书馆

2024 Conference on Lasers and Electro-Optics/Pacific Rim, CLEO-PR 2024

作者： Chang, Chenliang Dai, Bo Zhuang, Songlin Zhang, Dawei School of Optical-Electrical and Computer Engineering Engineering Research Center of Optical Instrument and System Ministry of Education Shanghai Key Laboratory of Modern Optics System University of Shanghai for Science and Technology Shanghai200093 China

In the field of computer holography, generating three-dimensional (3D) computer-generated hologram (CGH) in real-time speed has been a significant challenge due to the huge amount of data in 3D object wave. Deep learning has been proposed to compute CGH very fast using convolutional neural network (CNN). However, the input of the such CNN still depends on the acquisition of 3D information like RGB-D image. Here we present novel deep learning based computer holography technique which can rapidly generate CGH using CNN directly from stereo/single images rather than from RGB-D data. The method can simplify the CGH generation by using images as input, therefore avoiding the cumbersome 3D depth measuring process. © 2024 The Author(s)

关键词： Stereocenters

来源：评论

学校读者我要写书评

暂无评论

A TSE based design for MMSE and QRD of MIMO systems based on ASIP

引用

High technology Letters 2023年第2期29卷 166-173页

作者：冯雪林 SHI Jinglin CHEN Yang FU Yanlu ZHANG Qineng XIAO Feng Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing TechnologyChinese Academy of SciencesBeijing 100080P.R.China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049P.R.China Beijing Sylincom Technology Co. Ltd.Beijing 100190P.R.China

A Taylor series expansion(TSE) based design for minimum mean-square error(MMSE) and QR decomposition(QRD) of multi-input and multi-output(MIMO) systems is proposed based on application specific instruction set processor(ASIP), which uses TSE algorithm instead of resource-consuming reciprocal and reciprocal square root(RSR) *** aim is to give a high performance implementation for MMSE and QRD in one programmable platform ***, instruction set architecture(ISA) and the allocation of data paths in single instruction multiple data-very long instruction word(SIMD-VLIW) architecture are provided, offering more data parallelism and instruction parallelism for different dimension matrices and operation ***, multiple level numerical precision can be achieved with flexible table size and expansion order in TSE *** ASIP has been implemented to a 28 nm CMOS process and frequency reaches 800 *** results show that the proposed design provides perfect numerical precision within the fixed bit-width of the ASIP, higher matrix processing rate better than the requirements of 5G system and more rate-area efficiency comparable with ASIC implementations.

关键词： multi-input and multi-output(MIMO) minimum mean-square error(MMSE) QR decomposition(QRD) Taylor series expansion(TSE) application specific instruction set processor(ASIP) instruction set architecture(ISA) single instruction multiple data(SIMD) very long instruction word(VLIW)

来源：评论

学校读者我要写书评

暂无评论

Working Smarter Not Harder: Hybrid Cooling for Deep Learning in Edge Datacenters

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable computing 2025年

作者： Pei, Qiangyu Yuan, Yongjie Hu, Haichuan Wang, Lin Zhang, Dong Yan, Bingheng Yu, Chen Liu, Fangming Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology 1037 Luoyu Road Wuhan430074 China Paderborn University TU Darmstadt Germany Jinan Inspur Data Co. Ltd. China Huazhong University of Science and Technology Peng Cheng Laboratory China

The proliferation of deep-learning-based mobile and IoT applications has driven the increasing deployment of edge datacenters equipped with domain-specific accelerators. The unprecedented computing power offered by these accelerators puts a heavy burden on the cooling system, motivating more potent cooling techniques like cold water cooling. However, we observe that cold water cooling results in significant energy waste in edge datacenters due to the fluctuating resource utilization both spatially and temporally. To tackle this issue, we propose the concept of "working smarter"by slowing down accelerators deliberately whenever possible and enabling warm water cooling during these times to achieve cooling efficiency. Based on this concept, we develop Hyco - a hybrid water cooling system tailored for edge datacenters running deep learning workloads. First, Hyco features a zone-based cooling architecture enabling dynamic switching between cold water and warm water cooling. Then, based on a lightweight latency estimation method, Hyco incorporates a learning-based scheduling scheme to determine "which"accelerator workers and "when"to slow down through an adaptive and intelligent power-latency trade-off for deep learning models. The simulation with real-world traces shows that Hyco reduces the cooling energy consumption by up to 34.74× while satisfying latency constraints more than 99% of the time for deep-learning-based applications. © 2016 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Attention-enhanced Relation Network for Few-shot Image Classification 23

Attention-enhanced Relation Network for Few-shot Image Class...

引用

6th International Conference on Image and Graphics Processing, ICIGP 2023

作者： Li, Jinyang Tong, Jiahui Gao, Guangyu Xu, Wenbin School of Computer Science and Technology Beijing Institute of Technology China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Optical Radiation Laboratory Beijing Institute of Environmental Characteristics Beijing100854 China

ISBN: (纸本)9781450398572

Traditional deep learning models firmly rely on a large amount of labeled data during pre-training. Whereas it lacks generalization in the face of unfamiliar categories. Recently, few-shot learning is a hot topic in computer vision to classify unseen classes with limited labels. A representative approach is to extract features from the support and query sets, respectively, and compare similarities via metric learning. However, convolutional neural networks often focus only on a local region and ignore the global region, which severely reduces the accuracy of the matching. Specifically, in this paper, we pile lightweight attention-based blocks in the embedding module, which combines an adaptive kernel size 2D convolutional network with a cross-channel attention mechanism to encode multi-scale features and implicitly increase the receptive field. The SE-relation module chooses to construct learnable non-linear comparators to compare the relationship utilizing channel information. Finally, we show experimental results on standard few-shot testing benchmarks such as mini-ImageNet and tiered-ImageNet to demonstrate effectiveness. © 2023 ACM.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

GradedDAG: An Asynchronous DAG-based BFT Consensus with Lower Latency

GradedDAG: An Asynchronous DAG-based BFT Consensus with Lowe...

引用

Reliable Distributed systems

作者： Xiaohai Dai Zhaonan Zhang Jiang Xiao Jingtao Yue Xia Xie Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China School of Computer Science and Technology Hainan University China

To enable parallel processing, the Directed Acyclic Graph (DAG) structure is introduced to the design of asyn-chronous Byzantine Fault Tolerant (BFT) consensus protocols, known as DAG-based BFT. Existing DAG-based BFT protocols operate in successive waves, with each wave containing three or four Reliable Broadcast (RBC) rounds to broadcast data, resulting in high latency due to the three communication steps required in each RBC. For instance, Tusk, a state-of-the-art DAG-based BFT protocol, has a good-case latency of 7 communication steps and an expected worst latency of 21 communication steps. To reduce latency, we propose GradedDAG, a new DAG-based BFT consensus protocol based on our adapted RBC called Graded RBC (GRBC) and the Consistent Broadcast (CBC), with each wave consisting of only one GRBC round and one CBC round. Through GRBC, a replica can deliver data with a grade of 1 or 2, and a non-faulty replica delivering the data with grade 2 can ensure that more than 2/3 of replicas have delivered the same data. Meanwhile, through CBC, data delivered by different non-faulty replicas must be identical. In each wave, a block in the GRBC round will be elected as the leader. If a leader block has been delivered with grade 2, it and all its ancestor blocks can be committed. GradedDAG offers a good-case latency of 4 communication steps and an expected worst latency of 7.5 communication steps, significantly lower than the state-of-the-art. Experimental results demonstrate GradedDAG's feasibility and efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Latency and Energy Consumption for Mobile Edge computing Based Proximity Detection in Road Networks

引用

China Communications 2022年第4期19卷 274-290页

作者： Tongyu Zhao Yaqiong Liu Guochu Shou Xinwei Yao School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China Beijing Laboratory of Advanced Information Networks Beijing Key Laboratory of Network System Architecture and ConvergenceBeijing 100876China School of Computer Science and Technology Zhejiang University of TechnologyChina

In recent years, artificial intelligence and automotive industry have developed rapidly, and autonomous driving has gradually become the focus of the industry. In road networks, the problem of proximity detection refers to detecting whether two moving objects are close to each other or not in real time. However, the battery life and computing capability of mobile devices are limited in the actual scene,which results in high latency and energy consumption. Therefore, it is a tough problem to determine the proximity relationship between mobile users with low latency and energy consumption. In this article, we aim at finding a tradeoff between latency and energy consumption. We formalize the computation offloading problem base on mobile edge computing(MEC)into a constrained multiobjective optimization problem(CMOP) and utilize NSGA-II to solve it. The simulation results demonstrate that NSGA-II can find the Pareto set, which reduces the latency and energy consumption effectively. In addition, a large number of solutions provided by the Pareto set give us more choices of the offloading decision according to the actual situation.

关键词： proximity detection mobile edge computing road networks constrained multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Fast mode decomposition for few-mode fiber based on lightweight neural network

引用

Chinese Optics Letters 2024年第2期22卷 88-95页

作者：赵佳佳陈国辉毕轩蔡汪洋岳磊唐明 School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha 410114China Wuhan National Laboratory for Optoelectronics(WNLO)and National Engineering Laboratory for Next Generation Internet Access System School of Optical and Electronic InformationHuazhong University of Science and TechnologyWuhan 430074China

In this paper,we present a fast mode decomposition method for few-mode fibers,utilizing a lightweight neural network called *** method can quickly and accurately predict the amplitude and phase information of different modes,enabling us to fully characterize the optical field without the need for expensive experimental *** train the MobileNetV3-Light using simulated near-field optical field maps,and evaluate its performance using both simulated and reconstructed near-field optical field *** validate the effectiveness of this method,we conduct mode decomposition experiments on a few-mode fiber supporting six linear polarization(LP)modes(LP01,LP11e,LP11o,LP21e,LP21o,LP02).The results demonstrate a remarkable average correlation of 0.9995 between our simulated and reconstructed near-field lightfield *** the mode decomposition speed is about 6 ms per frame,indicating its powerful real-time processing *** addition,the proposed network model is compact,with a size of only 6.5 MB,making it well suited for deployment on portable mobile devices.

关键词： deep learning lightweight neural network few-mode fiber mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Does Your Neural Code Completion Model Use My Code? A Membership Inference Approach

arXiv

引用

arXiv 2024年

作者： Wan, Yao Wan, Guanghua Zhang, Shijie Zhang, Hongyu Zhou, Pan Jin, Hai Sun, Lichao National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Huazhong University of Science and Technology China University of Leigh United States

Recent years have witnessed significant progress in developing deep learning-based models for automated code completion. Examples of such models include CodeGPT and StarCoder. These models are typically trained from a large amount of source code collected from open-source communities such as GitHub. Although using source code in GitHub has been a common practice for training deep-learning-based models for code completion, it may induce some legal and ethical issues such as copyright infringement. In this paper, we investigate the legal and ethical issues of current neural code completion models by answering the following question: Is my code used to train your neural code completion model? To this end, we tailor a membership inference approach (termed CodeMI) that was originally crafted for classification tasks to a more challenging task of code completion. In particular, since the target code completion models perform as opaque black boxes, preventing access to their training data and parameters, we opt to train multiple shadow models to mimic their behavior. The acquired posteriors from these shadow models are subsequently employed to train a membership classifier. Subsequently, the membership classifier can be effectively employed to deduce the membership status of a given code sample based on the output of a target code completion model. We comprehensively evaluate the effectiveness of this adapted approach across a diverse array of neural code completion models, (i.e., LSTM-based, CodeGPT, CodeGen, and StarCoder). Experimental results reveal that the LSTM-based and CodeGPT models suffer the membership leakage issue, which can be easily detected by our proposed membership inference approach with an accuracy of 0.842, and 0.730, respectively. Interestingly, our experiments also show that the data membership of current large language models of code, e.g., CodeGen and StarCoder, is difficult to detect, leaving amper space for further improvement. Finally, we also t

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Global and Local Information for Anomaly Detection with Normal Samples

Exploring Global and Local Information for Anomaly Detection...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Xu, Fan Wang, Nan Zhao, Xibin School of Computer Science and Technology University of Science and Technology of China Hefei230026 China School of Software Beijing Jiaotong University Beijing100044 China Key Laboratory for Information System Security Beijing100084 China

ISBN: (纸本)9798350337020

Anomaly detection aims to detect data that do not conform to regular patterns, and such data is also called outliers. The anomalies to be detected are often tiny in proportion, containing crucial information, and are suitable for application scenes like intrusion detection, fraud detection, fault diagnosis, e-commerce platforms, et al. However, in many realistic scenarios, only the samples following normal behavior are observed, while we can hardly obtain any anomaly information. To address such problem, we propose an anomaly detection method GALDetector which is combined of global and local information based on observed normal samples. The proposed method can be divided into a three-stage method. Firstly, the global similar normal scores and the local sparsity scores of unlabeled samples are computed separately. Secondly, potential anomaly samples are separated from the unlabeled samples corresponding to these two scores and corresponding weights are assigned to the selected samples. Finally, a weighted anomaly detector is trained by loads of samples, then the detector is utilized to identify else anomalies. To evaluate the effectiveness of the proposed method, we conducted experiments on three categories of real-world datasets from diverse domains, and experimental results show that our method achieves better performance when compared with other state-of-the-art methods. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Previs-Real:Interactive virtual previsualization system for news shooting rehearsal and evaluation

引用

虚拟现实与智能硬件（中英文） 2024年第6期6卷 527-549页

作者： Che QU Shaocong WANG Chao ZHOU Tongchen ZHAO Rui GUO Cheng Wa WONG Chi DENG Bin JI Yuhui WEN Yuanchun SHI Yong-Jin LIU Department of Film and Television Technology Beijing Film AcademyBeijing 100088China Department of Computer Science and Technology MOE-Key Laboratory of Pervasive ComputingTsinghua UniversityBeijing 100084China School of Social Sciences Tsinghua UniversityBeijing 100084China News Production and Broadcasting First Division China Media GroupBeijing 100038China School of Computer and Information Technology Bejing Jiaotong UniversityBejing 100044China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong UniversityBeijing 100044China

Background In the demanding field of live news broadcasting,the intricate studio production procedures and tight schedules pose significant challenges for physical rehearsals by *** paper explores the design and implementation of a lightweight virtual news previsualization system,leveraging virtual production technology and interaction design methods to address the lack of fidelity in presentations and manipulations,and the quantitative feedback of rehearsal effects in previous virtual *** Our system,Previs-Real,is informed by user investigation with professional cameramen and studio technicians,and adheres to principles of high fidelity,accurate replication of actual hardware operations,and real-time feedback on rehearsal *** system's software and hardware development are implemented based on Unreal Engine and accompanying toolsets,incorporating cutting-edge modeling and camera calibration *** We validated Previs-Real through a user study,demonstrating superior performance in previsualization shooting tasks using the virtual system compared to traditional camera *** findings,supported by both objective performance metrics and subjective responses,underline Previs-Real's effectiveness and potential in transforming news broadcasting *** Previs-Real eliminates the requirement for complex equipment interconnections and team coordination inherent in a physical studio by implementing methodologies complying the above principles,objectively resulting in a lightweight design of applicable version of virtual news previsualization *** offers a novel solution to the challenges in news studio previsualization by focusing on key operational features rather than full environment *** design approach is equally effective in the process of designing lightweight systems in other fields.

关键词： News broadcast Previsualization Human computer interaction design User-centered design Interface evaluation

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：