检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Tang, Yu Wang, Chenyu Zhang, Yufan Liu, Yuliang Zhang, Xingcheng Qiao, Linbo Lai, Zhiquan Li, Dongsheng Science and Technology on Parallel and Distributed Processing Laboratory United States SenseTime Research Shanghai Artificial Intelligence Laboratory China

Training activations of deep neural networks occupy plenty of GPU memory, especially for large-scale deep neuralnetworks. However, the further development of deep neural networks is hampered by the limited GPU memory resource. Therefore, the optimal utilization of GPU memory resources is highly demanded. Swapping and recomputation are commonly applied to make better use of GPU memory in deep learning. As an emerging domain, several dilemmas remain: 1) The efficiency of recomputation is limited and swapping between GPU and CPU costs severe time delay;2) There still lacks a dynamic runtime memory manager of tensor swapping and tensor recomputation nowadays;3) Manually decisions for activations of training deep neural network require professional priors and experience. To remedy the above issues, we propose a novel memory manager named DELTA (Dynamic tEnsor offLoading and recompuTAtion). To the best of our knowledge, we are the first to propose a reasonable dynamic runtime manager on the combination of tensor swapping and tensor recomputation without user oversight. In DELTA, we firstly propose a filter algorithm to select the optimal tensors to be released out of GPU memory and secondly present a director algorithm to select a proper action for each of these tensors. Furthermore, prefetching and overlapping are deliberately considered to overcome the time cost caused by swapping and recomputing tensors. Experimental results show that DELTA not only saves 40%-70% of GPU memory, surpassing the state-of-the-art method to a great extent, but also gets comparable convergence results as the baseline with acceptable time delay. Also, DELTA gains 2.04× maximum batchsize when training ResNet-50 and 2.25× when training ResNet-101 compared with the baseline. Besides, comparisons between the swapping cost and recomputation cost in our experiments demonstrate the importance of making a reasonable decision on tensor swapping and tensor recomputation, which refutes the arguments in

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

A technical capability evaluation model based concept and prerequisite relation in computer education 33

A technical capability evaluation model based concept and pr...

引用

33rd International Conference on Software Engineering and Knowledge Engineering, SEKE 2021

作者： Luo, Jiwen Wang, Tao Chang, Junsheng Guo, Xiaoting National Key Laboratory for Parallel and Distributed Processing College of Computer National University of Defense Technology Changsha410073 China

ISBN: (纸本)1891706527

Effectively assessing the results of users' online learning and enhancing social recognition has become a major development direction for online education platforms. For computer education, this article constructs a technical capability assessment model. This model integrates professional concepts in the field of computer science and extracts knowledge concepts from educational resources. The model first extracts candidate concepts, then uses a graph propagation algorithm to quantify candidate concepts and obtains concepts from them, and finally uses prerequisite relationships to further quantify the concepts mastered by students. The model combines the prerequisite relationship among concepts to quantify the skills that students have mastered. It can not only effectively evaluate the user's skill mastery but also lays a foundation for subsequent course recommendations and career recommendations for users. The model is tested in the real learning environment of 250 students. This model has been proved to own certain practicability and reliability by Kendall rank correlation coefficient, which is used as an evaluation index. © 2021 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A data-assisted physics-informed neural network(DA-PINN)for fretting fatigue lifetime prediction

引用

International Journal of Mechanical System Dynamics 2024年第3期4卷 361-373页

作者： Can Wang Qiqi Xiao Zhikun Zhou Yongyu Yang Gregor Kosec Lihua Wang Magd Abdel Wahab Soete Laboratory Department of Electrical EnergyMetalsMechanical Constructions and SystemsFaculty of Engineering and ArchitectureGhent UniversityGentBelgium Department of Engineering Mechanics School of Aerospace EngineeringHuazhong University of Science and TechnologyWuhanChina Key Laboratory for Mechanics Anhui Polytechnic UniversityWuhuChina Parallel and Distributed Systems Laboratory Jožef Stefan InstituteLjubljanaSlovenia School of Aerospace Engineering and Applied Mechanics Tongji UniversityShanghaiChina College of Engineering Yuan Ze UniversityTaiwanChina

In this study,we present for the first time the application of physics-informed neural network(PINN)to fretting fatigue *** PINN has recently been applied to pure fatigue lifetime prediction,it has not yet been explored in the case of fretting *** propose a data-assisted PINN(DA-PINN)for predicting fretting fatigue crack initiation *** traditional PINN that solves partial differential equations for specific problems,DA-PINN combines experimental or numerical data with physics equations as part of the loss function to enhance prediction *** DA-PINN method,employed in this study,consists of two main ***,damage parameters are obtained from the finite element method by using critical plane method,which generates a data set used to train an artificial neural network(ANN)for predicting damage parameters in other ***,the predicted damage parameters are combined with the experimental parameters to form the input data set for the DA-PINN models,which predict fretting fatigue *** results demonstrate that DA-PINN outperforms ANN in terms of prediction accuracy and eliminates the need for high computational costs once the damage parameter data set is ***,the choice of loss-function methods in DA-PINN models plays a crucial role in determining its performance.

关键词： crack initiation data-assisted fretting fatigue finite element method physics-informed neural network

来源：评论

学校读者我要写书评

暂无评论

A Deeply Pipelined 64-bit Multiplier for High-Performance RISC-V Processors

A Deeply Pipelined 64-bit Multiplier for High-Performance RI...

引用

Frontiers technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Wenyi Liu Feng Hu Guilan Li Bangjian Xu Xin Niu College of Computer Science and Electronic Hunan University Changsha China Science and Technology on Parallel and Distributed Laboratory College of Computer National University of Defense Technology Changsha China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

The multiplier is an important component of the processor's computing unit. Multiplication, multiplication, addition, and multiplication and subtraction operations are widely used in various signal processing algorithms. Based on this, this article extends the multiplication instructions of RISC-V, designs a 64-bit multiplier that combines the booth2 algorithm and wallace compression technology, and designs a deep pipeline mechanism for the multiplier to improve performance. Finally, Through logical simulation and emulation, the result output is correct. Comprehensive results show that under the 28nm cmos process, the MAC unit can reach 2.22Ghz.

关键词： Program processors Pipelines Emulation Signal processing algorithms Computer architecture CMOS process Encoding Circuit synthesis Testing

来源：评论

学校读者我要写书评

暂无评论

GNNRL-Smoothing: A Prior-Free Reinforcement Learning Model for Mesh Smoothing

arXiv

引用

arXiv 2024年

作者： Wang, Zhichao C. Chen, Xinhai C. Gong, Chunye Y. Yang, Bo Deng, Liang Sun, Yufei F. Pang, Yufei F. Liu, Jie National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory China National University of Defense Technology Laboratory of Digitizing Software for Frontier Equipment China China Aerodynamics Research and Development Center China Nankai University College of Software China

Mesh smoothing methods can enhance mesh quality by eliminating distorted elements, leading to improved convergence in simulations. To balance the efficiency and robustness of traditional mesh smoothing process, previous approaches have employed supervised learning and reinforcement learning to train intelligent smoothing models. However, these methods heavily rely on labeled dataset or prior knowledge to guide the models’ learning. Furthermore, their limited capacity to enhance mesh connectivity often restricts the effectiveness of smoothing. In this paper, we first systematically analyze the learning mechanisms of recent intelligent smoothing methods and propose a prior-free reinforcement learning model for intelligent mesh smoothing. Our proposed model integrates graph neural networks with reinforcement learning to implement an intelligent node smoothing agent and introduces, for the first time, a mesh connectivity improvement agent. We formalize mesh optimization as a Markov Decision Process and successfully train both agents using Twin Delayed Deep Deterministic Policy Gradient and Double Dueling Deep Q-Network in the absence of any prior data or knowledge. We verified the proposed model on both 2D and 3D meshes. Experimental results demonstrate that our model achieves feature-preserving smoothing on complex 3D surface meshes. It also achieves state-of-the-art results among intelligent smoothing methods on 2D meshes and is 7.16 times faster than traditional optimization-based smoothing methods. Moreover, the connectivity improvement agent can effectively enhance the quality distribution of the mesh. © 2024, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating a New Attention Framework Based on Matrix Blocking for Attention Models on FPGAs

Evaluating a New Attention Framework Based on Matrix Blockin...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Xiaohang Liu Jingfei Jiang Jinwei Xu Lei Gao National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China

The attention mechanism has recently shown superior performance in natural language processing and computer vision tasks. But its complex dataflow and large-scale matrix calculation with huge computing and memory overhead pose a great challenge for the design of hardware accelerators. And previous solutions that benefited from matrix partitioning are bounded by the softmax function. In this paper, we propose a new attention framework that can dramatically improve the performance of attention model inference for long sequence tasks on FPGAs. We design a novel accelerator architecture that employs two systolic arrays and a ping-pong structure to accelerate attention calculation. Meanwhile, we propose an analytical model to predict resource usage and performance, which guides a fast design space exploration. Experiments using the state-of-the-art BERT demonstrate the design achieves 4.61 and 1.24× improvement in speed and energy efficiency compared to CPU and GPU on the Xilinx XCZU11EG platform.

关键词： Performance evaluation Graphics processing units Accelerator architectures Systolic arrays Natural language processing Mobile handsets Space exploration

来源：评论

学校读者我要写书评

暂无评论

WBA: A Warping-based Approach to Generating Imperceptible Adversarial Examples

WBA: A Warping-based Approach to Generating Imperceptible Ad...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Chengyao Hua Shigeng Zhang Weiping Wang Zhankai Li Jian Zhang School of Computer Science and Engineering Central South University Changsha China Science and Technology on Parallel and Distributed Processing Laboratory (PDL)

The human can easily recognize the incongruous parts of an image, for example, perturbations unrelated to the image itself, but are poor at spotting the small geometric transformations. However, in terms of the robustness of deep neural networks (DNNs), the ability to properly recognize objects with small geometric transformations is still a challenge. In this work, we investigate the problem from the perspective of adversarial attacks: does the performance of DNNs degrade even when small geometric transformations are applied to images? To this end, we propose a novel adversarial attack method, called WBA, a Warping-Based Adversarial attack method, which does not introduce information independent of the original images but manipulates the existing pixels of the images by elastic warping transformations to generate adversarial examples that are imperceptible to the human eye. At the same time, existing adversarial attacks typically generate adversarial examples by modifying pixels in the spatial domain of the image, the addition of such perturbations introduces extra information unrelated to the image itself and is easily detected by the naked eyes. We demonstrate the effectiveness of WBA by extensive experiments on commonly used datasets, including MNIST, CIFAR10, and ImageNet. The results show that WBA can quickly generate adversarial examples with the highest adversarial strength, consumes less time, and can be comparable to optimization-based adversarial attack methods in image perception evaluation metrics such as LPIPS, SSIM, and far more than gradient direction-based iterative methods.

关键词： Measurement Deep learning Privacy Image recognition Perturbation methods Neural networks Robustness

来源：评论

学校读者我要写书评

暂无评论

LRT-DETR: An Enhanced Transformer-Based Framework for PCB Surface Defect Detection

LRT-DETR: An Enhanced Transformer-Based Framework for PCB Su...

引用

Artificial Intelligence, Networking and Information technology (AINIT), International Seminar on

作者： Hongyu Tang Dengli Bu Guanhao Mo Panlin Lu Zhenhai Li Long Huang Key Laboratory of Intelligent Computing and Distributed Information Processing School of Computer Science and Technology Guangxi University of Science and Technology Guangxi Colleges and Universities Liuzhou China

ISBN: (数字)9798331522285

ISBN: (纸本)9798331522292

To address the issues of complex background interference and micro-defect detection in printed circuit board (PCB) surface inspection, while accommodating the deployment constraints of edge devices in industrial scenarios, this paper proposes a lightweight real-time detection Transformer (LRTDETR), an improved architecture based on RT-DETR. First, the original ResNet18 backbone is replaced with RepNCSPELAN, a lightweight network leveraging structural re-parameterization to reduce model complexity. Second, a global-local bidirectional feature pyramid network is introduced in the neck, which enhances the multi-scale feature representation through an adaptive weighted feature fusion mechanism, significantly improving small defect detection. Experimental results demonstrate that the improved model achieves a 96.9% mean average precision (mAP) with only a 0.2% performance drop compared to the baseline. Notably, the model size, the parameters, and the FLOPs are reduced by $58.3 \%, 53.5 \%$ , and 57.3%, respectively. The inference speed reaches 39 FPS, balancing accuracy and efficiency for real-time industrial inspection and edge deployment. This work provides a practical solution for highprecision, resource-efficient defect detection in industrial edge computing environments.

关键词： Adaptation models Computational modeling Image edge detection Printed circuits Inspection Feature extraction Transformers Real-time systems Neck Defect detection

来源：评论

学校读者我要写书评

暂无评论

An empirical study on the structure evolution of deep learning models: taking SAR image processing a case study

An empirical study on the structure evolution of deep learni...

引用

IEEE International Conference on Joint Cloud Computing (JCC)

作者： Huanxi Liu Xiang He Dawei Feng Han Bao National Laboratory for Parallel and Distributed Processing (PDL) National University of Defense Technology China School of Information and Communication National University of Defense Technology China

With the continuous improvement on model performance, deep learning models have been widely deployed and achieved promising outcomes in various fields in recent years. However, due to the escalating volumes of training data and the complexity of application problems, it becomes more and more challenging to design a neural network with better performance by hand. Analysing the evolution of typical neural network structures has important reference significance for designing a network structure. In this paper, we select the open source models in SAR image processing for an empirical analysis on the evolution of neural network structures. We analyse the evolution of 239 open source deep learning models from the aspects of framework, computing unit, model computation amount and the combined use of various computing units. Results reveal that preference and co-occurrence exist in computing units, while the average number of convolution, activation and normalization layer increases significantly over time. Model complexity shows an overall upward trend, and the characteristics of SAR image are more and more taken into consideration during the model structure design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CMT-YARN: an efficient security framework for yarn based on an improved merkle tree

引用

The Journal of Supercomputing 2025年第10期81卷 1-30页

作者： Liu, Peihao Luo, Daojie Liu, Jiahua Deng, Junyi Bu, Dengli Wang, Huan Yan, Junjie School of Computer Science and Technology Guangxi University of Science and Technology Liuzhou China Guangxi Colleges and Universities Key Laboratory of Intelligent Computing and Distributed Information Processing Liuzhou China School of Electronic Engineering Guangxi University of Science and Technology Liuzhou China

Hadoop is one of the most popular platforms for distributed big data processing, and YARN is at the core of Hadoop 2.0. During data processing, malicious nodes may compromise results by sharing incorrect outputs in the public cloud. To address this issue, this paper introduces an efficient YARN security framework, termed CMT-YARN, which incorporates an enhanced convolutional Merkle tree (CMHT) to ensure the reliability of task execution results. In a hybrid cloud environment, CMT-YARN leverages the improved CMHT technique for dual verification of intermediate and final results, ensuring data integrity and reliability. Compared to the conventional Merkle tree, CMHT reduces computational overhead by more than 37% during verification. Qualitative and quantitative analyzes indicate that with a data sampling rate of 6.8%, CMT-YARN can ensure that the number of malicious acts undetected by the system does not exceed 5; when the sampling rate exceeds 26.9%, the framework can guarantee the detection of all malicious activities. Experimental results on a real Hadoop cluster demonstrate that CMT-YARN significantly enhances computational and storage performance compared to traditional solutions.

关键词：

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：