检索结果-内蒙古大学图书馆

FDGLib: A Communication Library for Efficient Large-Scale Graph Processing in FPGA-Accelerated Data Centers

Journal of computer Science & Technology 2021年第5期36卷 1051-1070页

作者： Yu-Wei Wu Qing-Gang Wang Long Zheng Xiao-Fei Liao Hai Jin Wen-Bin Jiang Ran Zheng Kan Hu National Engineering Research Center for Big Data Technology and System School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Services Computing Technology and System Laboratory School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Cluster and Grid Computing Laboratory School of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China

With the rapid growth of real-world graphs,the size of which can easily exceed the on-chip(board)storage capacity of an accelerator,processing large-scale graphs on a single Field Programmable Gate Array(FPGA)becomes *** multi-FPGA acceleration is of great necessity and *** cloud providers(e.g.,Amazon,Microsoft,and Baidu)now expose FPGAs to users in their data centers,providing opportunities to accelerate large-scale graph *** this paper,we present a communication library,called FDGLib,which can easily scale out any existing single FPGA-based graph accelerator to a distributed version in a data center,with minimal hardware engineering *** provides six APIs that can be easily used and integrated into any FPGA-based graph accelerator with only a few lines of code *** the torus-based FPGA interconnection in data centers,FDGLib also improves communication efficiency using simple yet effective torus-friendly graph partition and placement *** interface FDGLib into AccuGraph,a state-of-the-art graph *** results on a 32-node Microsoft Catapult-like data center show that the distributed AccuGraph can be 2.32x and 4.77x faster than a state-of-the-art distributed FPGA-based graph accelerator ForeGraph and a distributed CPU-based graph system Gemini,with better scalability.

关键词： data center accelerator graph processing distributed architecture communication optimization

来源：评论

学校读者我要写书评

暂无评论

Adversarial Learning Under Hybrid Perturbations for Robust Acute Lymphoblastic Leukemia Classification 39

Adversarial Learning Under Hybrid Perturbations for Robust A...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Jie Liu, Xinyuan Liu, Xintong Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

ISBN: (纸本)157735897X

Acute lymphoblastic leukemia is a childhood cancer prevalent worldwide, which can prove fatal within weeks or months. However, current diagnosis models based on machine learning and deep learning methods fail to consider device noise (pixel-level perturbations) and rotation/translation (spatial-transformed perturbations), which can undermine the model's robustness. Adversarial training is a potential solution to this issue. This paper presents a hybrid perturbation adversarial training (HPAT) strategy that leverages two types of adversarial samples: pixel-level adversarial samples and spatial adversarial samples. This work generates these hybrid adversarial samples through Projected Gradient Descent (PGD) in couple with spatial transformation based on the Bayesian optimization (STBO) algorithm, respectively. This work introduced the Mixed Batch Normalization (MixBN) module to handle both adversarial samples and clean samples, alleviating the problem of clean accuracy degradation due to adversarial training. The proposed hybrid adversarial training strategy is tested on the public acute lymphoblastic leukemia dataset and found that it outperformed existing acute lymphoblastic cell classification models. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Generative artificial intelligence and its applications in materials science:Current situation and future perspectives

引用

Journal of Materiomics 2023年第4期9卷 798-816页

作者： Yue Liu Zhengwei Yang Zhenyao Yu Zitu Liu Dahui Liu Hailong Lin Mingqing Li Shuchang Ma Maxim Avdeev Siqi Shi School of Computer Engineering and Science Shanghai UniversityShanghai200444China State Key Laboratory of Advanced Special Steel School of Materials Science and EngineeringShanghai UniversityShanghai200444China Materials Genome Institute Shanghai UniversityShanghai200444China Shanghai Engineering Research Center of Intelligent Computing System Shanghai200444China Australian Nuclear Science and Technology Organisation Sydney2232Australia School of Chemistry The University of SydneySydney2006Australia

Generative Artificial Intelligence(GAI)is attracting the increasing attention of materials community for its excellent capability of generating required *** the introduction of Prompt paradigm and reinforcement learning from human feedback(RLHF),GAI shifts from the task-specific to general pattern gradually,enabling to tackle multiple complicated tasks involved in resolving the structure-activity ***,we review the development status of GAI comprehensively and analyze pros and cons of various generative models in the view of *** applications of task-specific generative models involving materials inverse design and data augmentation are also *** ChatGPT as an example,we explore the potential applications of general GAI in generating multiple materials content,solving differential equation as well as querying materials ***,we summarize six challenges encountered for the use of GAI in materials science and provide the corresponding *** work paves the way for providing effective and explainable materials data generation and analysis approaches to accelerate the materials research and development.

关键词： Machine learning Artificial intelligence Generative artificial intelligence Materials science Novel materials discovery Deep learning

来源：评论

学校读者我要写书评

暂无评论

Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Deng, Songhe Zhuo, Wei Xie, Jinheng Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Class Activation Map (CAM) has emerged as a popular tool for weakly supervised semantic segmentation (WSSS), allowing the localization of object regions in an image using only image-level labels. However, existing CAM methods suffer from under-activation of target object regions and false-activation of background regions due to the fact that a lack of detailed supervision can hinder the model’s ability to understand the image as a whole. In this paper, we propose a novel Question-Answer Cross-Language-Image Matching framework for WSSS (QA-CLIMS), leveraging the vision-language foundation model to maximize the text-based understanding of images and guide the generation of activation maps. First, a series of carefully designed questions are posed to the VQA (Visual Question Answering) model with Question-Answer Prompt engineering (QAPE) to generate a corpus of both foreground target objects and backgrounds that are adaptive to query images. We then employ contrastive learning in a Region Image Text Contrastive (RITC) network to compare the obtained foreground and background regions with the generated corpus. Our approach exploits the rich textual information from the open vocabulary as additional supervision, enabling the model to generate high-quality CAMs with a more complete object region and reduce false-activation of background regions. We conduct extensive analysis to validate the proposed method and show that our approach performs state-of-the-art on both PASCAL VOC 2012 and MS COCO datasets. Code is available at: https://***/CVI-SZU/QA-CLIMS Copyright © 2024, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

A Cooperative Co-Evolution Algorithm with Variable-Importance Grouping for Large-Scale Optimization 13

A Cooperative Co-Evolution Algorithm with Variable-Importanc...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Li, Yongfeng Zhang, Yuze Ma, Lijia Ji, Junkai Liu, Dugang Leung, Victor C. M. Li, Jianqiang Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen518123 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen518172 China The University of British Columbia Department of Electrical and Computer Engineering VancouverV6T 1Z4 Canada

ISBN: (纸本)9798350308365

Cooperative co-evolution (CC) is a promising direction in solving large-scale multiobjective optimization problems (LMOPs). However, most existing methods of grouping decision variables face some difficulties when searching in the huge search space. Specifically, the methods of grouping decision variables can be classified into two types, i.e., high-consumption grouping methods and non-consumption grouping methods. On the one hand, the former ones divide the decision variables into different groups based on the correlation analysis between variables, which consume much evaluation. This way may lead to premature convergence within limited computational resources. On the other hand, the later ones allocate the decision variables into sub-groups based on some metrics, e.g., order and size, which consume no evaluation while may cause the search fall into local optima. To alleviate the above issues, this paper proposes a CC-based algorithm with a variable-importance grouping (VIG) method, called VICCA. Firstly, the decision variables are classified into several subgroups according to their importance quantified by a meta-gene construction method. Secondly, a CC strategy is designed to simultaneously optimize all subgroups of decision variables formed by VIG using the differential evolution operator, which aims to accelerate the convergence speed. Thirdly, a global evolutionary strategy is proposed to optimize original decision variable space by the competitive swarm optimizer, aiming to maintain the diversity. Finally, the experiments demonstrate that our proposed VICCA has the significant advantage in solving LMOPs when compared with state-of-the-art evolutionary algorithms. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A 200V Monolithic GaN Dynamic Floating Voltage Level Shifter with Nanosecond Propagation Delays and Noise-Immune Slewing Control

A 200V Monolithic GaN Dynamic Floating Voltage Level Shifter...

引用

Annual IEEE Conference on Applied Power Electronics Conference and Exposition (APEC)

作者： Fei Zhou D. Brian Ma Department of Electrical and Computer Engineering Integrated Power Electronics System Laboratory The University of Texas at Dallas Richardson TX USA

Monolithic GaN power IC has been regarded as the ultimate solution to unlock the full potential of the wide bandgap GaN technology for next-generation high-speed, high-efficiency and high-density power circuits. However, with scarce power device options, the current development of monolithic GaN power ICs faces severe design challenges. A critical example can be found in the design of one of the most important circuit modules – the voltage level shifter, which is the enabler to drive any kind of high-side power switch in a power circuit. To overcome this challenge, this paper proposes a new circuit structure and a novel operation concept of a dynamic floating voltage level shifter to reduce propagation delays, improve dynamic slew rates and attain superb dv⁄dt noise immunity for both speed and reliability improvements. Implemented on a 200V, 180nm, n-type only, GaN-on-SOI process, the proposed voltage level shifter only occupies a die area of 0.12mm 2 and achieves 2.81ns rising and 3.44ns falling propagation delays at room temperature with a slew rate of 100V/ ns.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On convergence of covariance matrix of empirical Bayes hyper-parameter estimator

引用

Control Theory and Technology 2024年第2期22卷 149-162页

作者： Yue Ju Biqiang Mu Tianshi Chen School of Data Science and Shenzhen Research Institute of Big Data The Chinese University of Hong KongShenzhenShenzhen518172GuangdongChina Division of Decision and Control Systems School of Electrical Engineering and Computer ScienceKTH Royal Institute of Technology10044StockholmSweden Key Laboratory of Systems and Control Institute of Systems ScienceAcademy of Mathematics and System ScienceChinese Academy of SciencesBeijing100190China

Regularized system identification has become the research frontier of system identification in the past *** related core subject is to study the convergence properties of various hyper-parameter estimators as the sample size goes to *** this paper,we consider one commonly used hyper-parameter estimator,the empirical Bayes(EB).Its convergence in distribution has been studied,and the explicit expression of the covariance matrix of its limiting distribution has been ***,what we are truly interested in are factors contained in the covariance matrix of the EB hyper-parameter estimator,and then,the convergence of its covariance matrix to that of its limiting distribution is *** general,the convergence in distribution of a sequence of random variables does not necessarily guarantee the convergence of its covariance ***,the derivation of such convergence is a necessary complement to our theoretical analysis about factors that influence the convergence properties of the EB hyper-parameter *** this paper,we consider the regularized finite impulse response(FIR)model estimation with deterministic inputs,and show that the covariance matrix of the EB hyper-parameter estimator converges to that of its limiting ***,we run numerical simulations to demonstrate the efficacy of ourtheoretical results.

关键词： Regularized system identification Hyper-parameter estimator Empirical Bayes Convergence of covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Toward High-Accuracy 3D Creation of Aviation Tools via Analysis-by-Synthesis

引用

IEEE Access 2025年 13卷 87208-87219页

作者： Gundu Mohamed Hassan Yoo Sung Kim Geun Sik Jo Department of Artificial Intelligence Engineering Knowledge Management System Laboratory Inha University Incheon South Korea Department of Computer Science Engineering Artificial Intelligence Laboratory Inha University Incheon South Korea Augmented Knowledge Corporation Incheon South Korea

The field of education is rapidly shifting toward digital platforms; however, aviation education continues to rely heavily on traditional paper-based manuals. This persistence is largely due to the inherent complexity, scale, and high costs associated with aviation equipment, making digital transformation particularly challenging. In this paper, we utilizing the analysis-by-synthesis method is presented for multi-view 3D reconstruction of solid objects, specifically focusing on aviation tools. To facilitate this research, a custom dataset was generated using Unity, enabling controlled experimentation and performance evaluation. Comparative analysis with existing benchmarks demonstrates that, despite the intricate nature of aviation tools compared to simpler objects. The proposed architecture effectively reconstructs detailed and accurate digital replicas with 97% accuracy. This advancement has the potential to significantly enhance aviation training by providing immersive, interactive 3D content, bridging the gap between traditional training materials and cutting-edge digital education tools.

关键词： Training Maintenance Rendering (computer graphics) Aircraft Three-dimensional displays Lighting Image reconstruction Atmospheric modeling Accuracy Pipelines

来源：评论

学校读者我要写书评

暂无评论

A Conduction-Loss-Conscious 4-Level Power Converter with Tri-Path Synchronous Rectification for High Step-Down DC-DC Conversion

A Conduction-Loss-Conscious 4-Level Power Converter with Tri...

引用

Annual IEEE Conference on Applied Power Electronics Conference and Exposition (APEC)

作者： Jin Woong Kwak D. Brian Ma Department of Electrical and Computer Engineering Integrated Power Electronics System Laboratory The University of Texas at Dallas Richardson TX USA

Multi-level power converters today are highly desirable for high step-down DC-DC conversions but face a serious challenge due to the inherent limitations of topology and operation, which severely impacts efficiency. To combat this challenge, this paper proposes a new operation strategy - tri-path synchronous rectification (TSR) to reduce conduction loss in each discharge phase significantly, which is regarded as a dominant factor to efficiency. The TSR strategy is non-intrusive and can be virtually applied to any multi-level converters without interrupting the original converter operation. To demonstrate the design ideas, a 4-level TSR converter prototype is designed and tested. It down-converts a 48V power source to an output voltage programmable from 1V to 2V with a maximum load of 25A and a peak efficiency of 90.8%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Large Scale Model Enabled Semantic Communications Based on Robust Knowledge Distillation

Large Scale Model Enabled Semantic Communications Based on R...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Ding, Kuiyuan Liu, Fangfang Yang, Yang Chen, Mingzhe Guo, Caili Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China University of Miami Department of Electrical and Computer Engineering The Institute for Data Science and Computing Coral GablesFL33146 United States Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing100876 China

ISBN: (纸本)9798350351255

Large scale artificial intelligence (AI) models possess excellent capabilities in semantic representation and understanding, making them particularly well-suited for semantic encoding and decoding. However, the substantial scale of these AI models imposes unacceptable computational resources and communication delays. To address this issue, we propose a semantic communication scheme based on robust knowledge distillation (RKD-SC) for large scale model enabled semantic communications. In the considered system, a transmitter extracts the features of the source image for robust transmission and accurate image classification at the receiver. To effectively utilize the superior capability of large scale model while make the cost affordable, we first transfer knowledge from a large scale model to a smaller scale model to serve as the semantic encoder. Then, to enhance the robustness of the system against channel noise, we propose a channel-aware autoencoder (CAA) based on the Transformer architecture. Experimental results show that the encoder of proposed RKD-SC system can achieve over 93.3% of the performance of a large scale model while compressing 96.67% number of parameters. Code: https://***/echojayne/RKD-SC. © 2024 IEEE.

关键词： Channel coding

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：