检索结果-内蒙古大学图书馆

2022 IEEE Conference on Telecommunications, Optics and computer science, TOCS 2022

作者： Yu, Shiying Liu, Jinmei Shu, Hang Cheng, Zhiwei Wuhan University School of Geodesy and Geomatics Wuhan430000 China Rutgers University School of Arts and Sciences New Jersey NJ08854 United States South West University School of Computer and Information Science Chongqing400010 China Xi'an University of Science and Technology Department of Architecture and Civil Engineering Xi'an710600 China

ISBN: (纸本)9781665470537

Handwritten digit recognition has been widely researched. Numerous classification methods have been proposed. This article improves the recognition of handwritten numbers method based on CNN neural network. Recognition of handwritten digits has made great progress, but due to insufficient recognition accuracy, it will have a certain impact on work efficiency. In this paper, a two-layer CNN network with two fully connected layers can achieve a good prediction performance. In our framework, the activation function used is the ReLU function, to some extent, this avoids the difficulties of gradient disappearance and gradient saturation. At the same time, dropout is added to the full connection layer to discard the neurons in the network with a certain probability, which can avoid certain accidents, and the final trained network will be more robust and the generalization performance will be stronger. This method effectively improves the accuracy of recognition in the final experiment, which achieves 98.75% accuracy on theMNIST dataset and 99.25% on the CIFAR-100 dataset. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks

arXiv

引用

arXiv 2022年

作者： Han, Husheng Hu, Xing Xu, Kaidi Dang, Pucheng Wang, Ying Zhao, Yongwei Du, Zidong Guo, Qi Yang, Yanzhi Chen, Tianshi SKL of Processors Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Cambricon Technologies Beijing China Department of Computer Science College of Computing & Informatics Drexel University Philadelphia19104 United States SKL of Computer Architecture Institute of Computing Technology CAS Beijing100190 China Department of Electrical and Computer Engineering Northeastern University Boston02115 United States

DNN-based video object detection (VOD) powers autonomous driving and video surveillance industries with rising importance and promising opportunities. However, adversarial patch attack yields huge concern in live vision tasks because of its practicality, feasibility, and powerful attack effectiveness. This work proposes Themis, a software/hardware system to defend against adversarial patches for real-time robust video object detection. We observe that adversarial patches exhibit extremely localized superficial feature importance in a small region with non-robust predictions, and thus propose the adversarial region detection algorithm for adversarial effect elimination. Themis also proposes a systematic design to efficiently support the algorithm by eliminating redundant computations and memory traffics. Experimental results show that the proposed methodology can effectively recover the system from the adversarial attack with negligible hardware overhead. © 2022, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Building Agile Workflow Microservice System for HPC Applications Based on Fast-start OSv 27

Building Agile Workflow Microservice System for HPC Applicat...

引用

27th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2021

作者： Hu, Qiang Ma, Lixian Shao, En Tan, Guangming Institute of Computing Technology CAS State Key Laboratory of Computer Architecture Beijing China University of Chinese Academy of Science Beijing China

ISBN: (纸本)9781665408783

The advances of containers have significantly promoted the development of microservice architecture. This architecture splits a monolithic application into multiple independent components and the container orchestrator manages these components by the container in the cloud environment. The feasibility of deploying high performance computing(HPC) applications as microservices has been proven, but the existing container orchestrator incurs a large performance overhead as there is interference between different containers on the same physical host. In this paper, we design an agile workflow microservice system for HPC applications with fast-start OSv. We consider improving HPC workflow performance from two aspects: single OSv startup time optimization and workflow orchestration optimization. For single OSv startup time optimization, we design a fast-start OSv by analyzing the process of OSv startup and finding an optimization by modifying OSv source code. In this way, we get nearly 50% improvement of startup time. For workflow orchestration optimization, we propose four optimization techniques to speed up the execution of workflow by jointly considering OSv and workflow features, namely: node fusion, node merge, image preload, boot delay. Furthermore, we utilize our fast startup OSv to design an orchestration system for efficiently building an agile HPC workflow microservice by Kubevirt. Our experimental results optimization microservice system reduces the execution time by 30% compared with the original deployment with docker. © 2021 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Practice research of the training mode of students' innovative and entrepreneurial talents based on computer courses 16

Practice research of the training mode of students' innovati...

引用

16th IEEE International Conference on computer science and Education, ICCSE 2021

作者： Zhou, Yi Yu, Zhe Yu, Kang-Bo Wang, He Chen, Ling-Ling Changshu Institute of Technology College of Computer Science and Engineering SuZhou China Harbin Branch of United Network Telecommunications Corporation Harbin China Central China University Technology School of Architecture and Art ChangSha China Changshu Institute of Technology College of Computer Science and Technology SuZhou China

ISBN: (纸本)9781665414685

At present, the innovation and entrepreneurship education system of college students in colleges and universities in our country is faced with the problems of single resources, disconnect from majors and emphasis on theory and practice, which seriously restrict the effect and efficiency of college students' innovation and entrepreneurship education. This paper puts forward the use of service learning in the teaching of computer courses to carry out teaching activities, through the revision of talent training programs and curriculum, optimize innovative entrepreneurship education resources, build innovative entrepreneurship education information platform and other measures to strengthen the management and implementation of innovative entrepreneurship education for college students, improve the effectiveness and efficiency of innovative entrepreneurship education in colleges and universities. © 2021 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Application of Digital Twin in Smart Battery Electric Vehicle: Industry 4.0

Application of Digital Twin in Smart Battery Electric Vehicl...

引用

2022 International Conference on IT and Industrial Technologies, ICIT 2022

作者： Shoukat, Muhammad Usman Yan, Lirong Du, Changqing Mair Raza, Muhammad U Adeel, Muhammad Khan, Tauqeer Wuhan University of Technology School of Automotive Engineering Wuhan430070 China Shenzhen University College of CS and SE Shenzhen518060 China Punjab Tianjin Univ. of Technology Department of Architecture Lahore53720 Pakistan Islamia College University Peshawar Department of Computer Science Peshawar25120 Pakistan

ISBN: (数字)9781665489454

ISBN: (纸本)9781665489454

It is believed that using electric vehicles (EVs) for transportation is essential for addressing environmental and sustainable development challenges. Current ecofriendly concerns, such as the fast depletion of fossil fuels, rising air pollution, rising energy demand, global warming, and climate change, have made it possible to electrify the transportation industry. EVs can address all of the aforementioned issues. For electric vehicles (EVs), and particularly those powered by lithium-ion (Li-ion) batteries, portable power supplies have become indispensable. Although Li- ion batteries have been the focus of EV research for a long time, issues like battery aging and safety have yet to be fully understood. According to our current understanding of smart technology, we have the ability to use the digital twin (DT) to overcome a problem that has been holding back battery development, as well as the preliminary DT applications in complicated systems such as industry 4.0. This research focuses on the characteristics of batteries and how they relate to their modeling, state estimation, remaining usable life prediction, safety, and control. We put together an analysis of some of the most current achievements in battery prognostics and health monitoring. Finally, we provide prospects for the development of DTs in the field of EV batteries. © 2022 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Optimization of antique assembly building frame construction based on BIM technology and Matlab genetic algorithm

引用

Applied Mathematics and Nonlinear sciences 2024年第1期9卷

作者： Zhang, Han Ping, Hongming School of Civil Engineering and Architecture Henan University of Science and Technology Henan Luoyang471000 China Department of Electrical and Computer Engineering University of Washington SeattleWA98101 United States

With the rapid development of science and technology, the traditional construction industry is facing the urgent need for transformation and upgrading, and how to achieve the performance optimization of the assembly building frame has become an urgent problem to be solved. The research constructs the antique assembly building frame using BIM technology and uses a Matlab genetic algorithm to optimize the model of the building frame. The efficacy of the optimized assembly building is analyzed, and the safety performance of the BIM-Matlab frame building proposed in this paper is compared with that of the traditional frame building and the anti-buckling frame building to explore the effectiveness of the performance optimization of the BIM-Matlab frame building. The values of the structural non-lateral stiffness ratio of the BIM-Matlab assembly building are all greater than or equal to 1, and the seismic shear weight ratio meets the requirements. The displacement ratio and inter-story displacement ratio meet the code requirements under all working conditions. The building foundation's zero stress zone is 0.00%, and the minimum stiffness-to-weight ratio value of 38.69 is enough to pass the overturning resistance and stability test. The BIM-Matlab framed building can endure earthquakes with greater intensity and safety reserves than conventional framed buildings and anti-flexural framed buildings, which are more secure in earthquakes. © 2024 Han Zhang et al., published by Sciendo.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

G-SEPM: Building an Accurate and Efficient Soft Error Prediction Model for GPGPUs

G-SEPM: Building an Accurate and Efficient Soft Error Predic...

引用

Supercomputing Conference

作者： Hengshan Yue Xiaohui Wei Guangli Li Jianpeng Zhao Nan Jiang Jingweijia Tan College of Computer Science and Technology Jilin University Changchun Jilin China SKL Computer Architecture ICT CAS University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781450384421

ISBN: (纸本)9781665483902

As GPUs become ubiquitous in large-scale general purpose HPC systems (GPGPUs), ensuring the reliable execution of such systems in the presence of soft errors is increasingly essential. To provide insights into how resilient GPU programs are toward soft errors, researchers typically rely on random Fault Injection (FI) to evaluate the tolerance of programs. However, it is expensive to obtain a statistically significant resilience profile and not suitable to identify all the error-critical fault sites of GPU programs. To address the above challenges, in this work, we build a GPGPU-based Soft Error Prediction Model (G-SEPM) that can replace FI to estimate the resilience characteristics of individual fault sites accurately and efficiently. We observe that the instruction-type, bit-position, bit-flip direction, and error propagation information have capabilities to characterize fault site resiliency. Leveraging these heuristic features, G-SEPM drives the machine learning model to reveal the hidden interactions among fault site resiliency and our observed features. Experimental results demonstrate that G-SEPM achieves high accuracy for fault site error estimation and critical fault site identification while introducing negligible overhead. In addition, G-SEPM can provide essential insight for programmers/architects to design more cost-effective soft error mitigation solutions.

关键词： Fault diagnosis Support vector machines Error analysis High performance computing Graphics processing units Estimation Predictive models

来源：评论

学校读者我要写书评

暂无评论

LACC:a hardware and software co-design accelerator for deep neural networks

引用

High technology Letters 2021年第1期27卷 62-67页

作者： Yu Yong Zhi Tian Zhou Shengyuan State Key Laboratory of Computer Architecture Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190P.R.China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049P.R.China Cambricon Technologies Ltd Beijing 100190P.R.China

With the increasing of data size and model size,deep neural networks(DNNs)show outstanding performance in many artificial intelligence(AI)*** the big model size makes it a challenge for high-performance and low-power running DNN on processors,such as central processing unit(CPU),graphics processing unit(GPU),and tensor processing unit(TPU).This paper proposes a LOGNN data representation of 8 bits and a hardware and software co-design deep neural network accelerator LACC to meet the *** data representation replaces multiply operations to add and shift operations in running *** accelerator achieves higher efficiency than the state-of-the-art DNN accelerators by domain specific arithmetic computing ***,LACC speeds up the performance per watt by 1.5 times,compared to the state-of-the-art DNN accelerators on average.

关键词： deep neural network(DNN) domain specific accelerator domain specific data type

来源：评论

学校读者我要写书评

暂无评论

Exploring the performance bound of cambricon accelerator in end-to-end inference scenario 2nd

Exploring the performance bound of cambricon accelerator in ...

引用

2nd International Symposium on Benchmarking, Measuring, and Optimization, Bench 2019

作者： Wang, Yifan Li, Chundian Zeng, Chen SKL of Computer Architecture Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783030495558

Deep learning algorithms have become pervasive in a broad range of industrial application scenarios. DianNao/Cambricon family is a set of energy-efficient hardware accelerators for machine learning, especially for deep learning, covering from edge embedded devices to cloud data centers. However, in the real application scenario, the complicated software stack and the extra overhead (memory copy) hinder the full exploitation of the accelerator performance. In this paper, we try to explore the performance bound of Cambricon accelerator MLU100 in end-to-end deep learning inference scenarios (from data/model load to inference results store). We leverage the offline model to bypass the general deep learning framework, use the multiple threads programming to fully exploit the parallelism of the multi-core accelerator and apply specific data structure to decrease the memory copy overhead. The evaluation results show that, for RetNet-50 on CIFAR-10 dataset, our optimization methods are 32.09$$\times $$ faster than the baseline of the optimized batch size (64), and achieve $$85\%$$ of the performance upper-bound on the Cambricon MLU100 board. © Springer Nature Switzerland AG 2020.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

ArmorCLIP: A Hybrid Defense Strategy for Boosting Adversarial Robustness in Vision-Language Models

arXiv

引用

arXiv 2024年

作者： Li, Yijun Liang, Yuhan Niu, Yumeng Shen, Qianhe Liu, Hangyu Computer Science and Technology Harbin Institute of Technology Shenzhen518055 China Faculty of Engineering University of Bristol BristolBS8 1TH United Kingdom Computer Science and Technology Beijing University of Civil Engineering and Architecture Beijing102612 China Computer Science Mathematics & Statistics University of Toronto Mississauga MississaugaL5L 1C6 Canada Xi'an Tieyi ICC Shanxi Xian710054 China

The robustness of Vision-Language Models (VLMs) such as CLIP is critical for their deployment in safety-critical applications like autonomous driving, healthcare diagnostics, and security systems, where accurate interpretation of visual and textual data is essential. However, these models are highly susceptible to adversarial attacks, which can severely compromise their performance and reliability in real-world scenarios. Previous methods have primarily focused on improving robustness through adversarial training and generating adversarial examples using models like FGSM, AutoAttack, and DeepFool. However, these approaches often rely on strong assumptions, such as fixed perturbation norms or predefined attack patterns, and involve high computational complexity, making them challenging to implement in practical settings. In this paper, we propose a novel adversarial training framework that integrates multiple attack strategies and advanced machine learning techniques to significantly enhance the robustness of VLMs against a broad range of adversarial attacks. Experiments conducted on real-world datasets, including CIFAR-10 and CIFAR-100, demonstrate that the proposed method significantly enhances model robustness. The fine-tuned CLIP model achieved an accuracy of 43.5% on adversarially perturbed images, compared to only 4% for the baseline model. The neural network model achieved a high accuracy of 98% in these challenging classification tasks, while the XGBoost model reached a success rate of 85.26% in prediction tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

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：