检索结果-内蒙古大学图书馆

Characterization of Memory Access in Deep Learning and Its Implications in Memory Management

computers, Materials & Continua 2023年第7期76卷 607-629页

作者： Jeongha Lee Hyokyung Bahn Institute of Artificial Intelligence and Software Ewha UniversitySeoul03760Korea Department of Computer Science and Engineering Ewha UniversitySeoul03760Korea

Due to the recent trend of software intelligence in the Fourth Industrial Revolution,deep learning has become a mainstream workload for modern computer *** the data size of deep learning increasingly grows,managing the limited memory capacity efficiently for deep learning workloads becomes *** this paper,we analyze memory accesses in deep learning workloads and find out some unique characteristics differentiated from traditional ***,when comparing instruction and data accesses,data access accounts for 96%–99%of total memory accesses in deep learning workloads,which is quite different from traditional ***,when comparing read and write accesses,write access dominates,accounting for 64%–80%of total memory ***,although write access makes up the majority of memory accesses,it shows a low access bias of 0.3 in the Zipf ***,in predicting re-access,recency is important in read access,but frequency provides more accurate information in write *** on these observations,we introduce a Non-Volatile Random Access Memory(NVRAM)-accelerated memory architecture for deep learning workloads,and present a new memory management policy for this *** considering the memory access characteristics of deep learning workloads,the proposed policy improves memory performance by 64.3%on average compared to the CLOCK policy.

关键词： Memory access deep learning machine learning memory access memory management CLOCK

来源：评论

学校读者我要写书评

暂无评论

Real-time Volume Preserving Constraints for Volumetric Model on GPU

引用

computers, Materials & Continua 2022年第10期73卷 831-848页

作者： Hongly Va Min-Hyung Choi Min Hong Department of Software Convergence Soonchunhyang UniversityAsan31538Korea Department of Computer Science and Engineering University of Colorado DenverDenver80217COUSA Department of Computer Software Engineering Soonchunhyang UniversityAsan31538Korea

This paper presents a parallel method for simulating real-time 3D deformable objects using the volume preservation mass-spring system method on tetrahedron *** general,the conventional mass-spring system is manipulated as a force-driven method because it is fast,simple to implement,and the parameters can be ***,the springs in traditional mass-spring system can be excessively elongated which cause severe stability and robustness issues that lead to shape restoring,simulation blow-up,and huge volume loss of the deformable *** addition,traditional method that uses a serial process of the central processing unit(CPU)to solve the system in every frame cannot handle the complex structure of deformable object in ***,the first order implicit constraint enforcement for a mass-spring model is utilized to achieve accurate visual realism of deformable objects with tough constraint *** this paper,we applied the distance constraint and volume conservation constraints for each tetrahedron element to improve the stability of deformable object simulation using the mass-spring system and behave the same as its real-world *** reduce the computational complexity while ensuring stable simulation,we applied a method that utilizes OpenGL compute shader,a part of OpenGL Shading Language(GLSL)that executes on the graphic processing unit(GPU)to solve the numerical problems *** applied the proposed methods to experimental volumetric models,and volume percentages of all objects are *** average volume percentages of all models during the simulation using the mass-spring system,distance constraint,and the volume constraint method were 68.21%,89.64%,and 98.70%,*** proposed approaches are successfully applied to improve the stability of mass-spring system and the performance comparison from our experimental tests also shows that the GPU-based method is faster than CPU-based implementation for all cases.

关键词： Deformable object simulation mass-spring system implicit constraint enforcement volume conservation constraint GPU parallel computing

来源：评论

学校读者我要写书评

暂无评论

An Overview for Trustworthy and Explainable Artificial Intelligence in Healthcare 28

An Overview for Trustworthy and Explainable Artificial Intel...

引用

2024 28th International Conference on Information Technology, IT 2024

作者： Arslanoglu, Kubra Karakose, Mehmet The University of Firat The Faculty of Engineering Department of Software Engineering Elazig Turkey The University of Firat The Faculty of Engineering Department of Computer Engineering Elazig Turkey

ISBN: (纸本)9798350369618

Recently, the increased use of artificial intelligence in healthcare has significantly changed the developments in the field of medicine. Medical centres have adopted AI applications and used it in many applications to predict disease diagnosis and reduce health risks in a predetermined way. In addition to Artificial Intelligence (AI) techniques for processing data and understanding the results of this data, Explainable Artificial Intelligence (XAI) techniques have also gained an important place in the healthcare sector. In this study, reliable and explainable artificial intelligence studies in the field of healthcare were investigated and the blockchain framework, one of the latest technologies in the field of reliability, was examined. Many researchers have used blockchain technology in the healthcare industry to exchange information between laboratories, hospitals, pharmacies, and doctors and to protect patient data. In our study, firstly, the studies whose keywords were XAI and Trustworthy Artificial Intelligence were examined, and then, among these studies, priority was given to current articles using Blockchain technology. Combining the existing methods and results of previous studies and organizing these studies, our study presented a general framework obtained from the reviewed articles. Obtaining this framework from current studies will be beneficial for future studies of both academics and scientists. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Predictive Caching of File System for Database Workload Management 1

Predictive Caching of File System for Database Workload Mana...

引用

1st International Conference on AIML-Applications for engineering and Technology, ICAET 2025

作者： Jadhav, Rohini Jadhav, Veena Pawar, Prajakta Kannaujia, Abhishek Kumar, Abhishek Gohil, Jayesh College of Engineering Department of Information Technology Pune India College of Engineering Department of Computer Engineering Pune India Bharati Vidyapeeth College of Engineering Department of Computer Engineering Lavale Pune India Veritas Principal Software Engineering India

ISBN: (纸本)9798350355611

The proactive caching technique known as 'predictive caching' attempts to improve file system performance by anticipating and pre-fetching data that is likely to be requested in the future. Conventional caching strategies, such LRU (Least Recently Used) and LFU (Least Frequently Used), base their decision on which material to keep in the cache on historical access patterns. Although these methods work well in many situations, they could not completely take advantage of the temporal and geographical proximity of file system access patterns, which could result in less-than-ideal cache use. Utilizing machine learning algorithms, statistical analysis, or heuristics, predictive caching makes predictions about future access patterns based on past data, system status, file properties, or user activity. So we propose a predictive caching technique which reduce access latency and boost system performance by pre-fetching and storing pertinent data ahead of time in anticipation of incoming data accesses. © 2025 IEEE.

关键词： Dynamic Data File Access Pattern Predictive Caching Random Forest Classifier

来源：评论

学校读者我要写书评

暂无评论

TSN vs I3D vs Pose-C3D: Action Recognition in Basketball using SpaceJam Dataset 24

TSN vs I3D vs Pose-C3D: Action Recognition in Basketball usi...

引用

7th International Conference on Computational Intelligence and Intelligent Systems, CIIS 2024

作者： Chiura, Tafadzwa Blessing Van Der Haar, Dustin Academy of Computer Science and Software Engineering Faculty of Science University of Johannesburg Gauteng Johannesburg South Africa

ISBN: (纸本)9798400717437

Most of the research conducted in action recognition is mainly focused on general human action recognition, and most of the available datasets support studies in general human action recognition. In more specific contexts, such as basketball, datasets that are as comprehensive and publicly available are limited. This study proposes taking three popular and mature methods in the field of action recognition, namely Temporal Segment Networks (TSN), Two-Stream CNN using Inflated 3D-convolutional Neural Networks (I3D) and Pose-C3D, and applying them to the SpaceJam dataset, which is a basketball-specific action dataset. All three experiments used pre-trained ImageNet models and were fine-tuned on the SpaceJam dataset. TSN was the oldest of the methods but obtained the best results of the three experiments, scoring a top-1 and top-5 accuracy of 59% and 96%, respectively. I3D was second best, with a top-1 and top-5 accuracy of 41% and 85%, respectively. Pose-C3D came in third, scoring a top-1 and top-5 accuracy of 15% and 50%, respectively. The results show that the models cannot distinguish significantly between some actions, such as ball in hand, pass and dribble. The study shows that it is feasible for context-specific fine-grain action recognition, but more needs to be done to discriminate against similar actions. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Visual Semantic Embedding Network for Image-Text Retrieval

引用

Journal of computer Science & Technology 2024年第4期39卷 811-826页

作者： Xue-Yang Qin Li-Shuang Li Jing-Yao Tang Fei Hao Mei-Ling Ge Guang-Yao Pang School of Computer Science and Technology Dalian University of TechnologyDalian 116024China School of Computer Science Shaanxi Normal UniversityXi’an 710119China School of Computer Engineering Weifang UniversityWeifang 261061China Guangxi Colleges and Universities Key Laboratory of Intelligent Industry Software Wuzhou UniversityWuzhou 543002 China

Image-text retrieval aims to capture the semantic correspondence between images and texts,which serves as a foundation and crucial component in multi-modal recommendations,search systems,and online *** mainstream methods primarily focus on modeling the association of image-text pairs while neglecting the advantageous impact of multi-task learning on image-text *** this end,a multi-task visual semantic embedding network(MVSEN)is proposed for image-text ***,we design two auxiliary tasks,including text-text matching and multi-label classification,for semantic constraints to improve the generalization and robustness of visual semantic embedding from a training ***,we present an intra-and inter-modality interaction scheme to learn discriminative visual and textual feature representations by facilitating information flow within and between ***,we utilize multi-layer graph convolutional networks in a cascading manner to infer the correlation of image-text *** results show that MVSEN outperforms state-of-the-art methods on two publicly available datasets,Flickr30K and MSCOCO,with rSum improvements of 8.2%and 3.0%,respectively.

关键词： image-text retrieval cross-modal retrieval multi-task learning graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

Support vector machine with discriminative low-rank embedding

引用

CAAI Transactions on Intelligence Technology 2024年第5期9卷 1249-1262页

作者： Guangfei Liang Zhihui Lai Heng Kong Computer Vision Institute College of Computer Science and Software EngineeringShenzhen UniversityShenzhenChina Shenzhen Institute of Artificial Intelligence and Robotics for Society ShenzhenChina Department of Breast and Thyroid Surgery BaoAn Central Hospital of ShenzhenShenzhenChina

Support vector machine(SVM)is a binary classifier widely used in machine ***,neglecting the latent data structure in previous SVM can limit the performance of SVM and its *** address this issue,the authors propose a novel SVM with discriminative low-rank embedding(LRSVM)that finds a discriminative latent low-rank subspace more suitable for SVM *** extension models of LRSVM are introduced by imposing different orthogonality constraints to prevent computational inaccuracies.A detailed derivation of the authors’iterative algorithms are given that is essentially for solving the SVM on the low-rank ***,some theorems and properties of the proposed models are presented by the *** is worth mentioning that the subproblems of the proposed algorithms are equivalent to the standard or the weighted linear discriminant analysis(LDA)*** indicates that the projection subspaces obtained by the authors’algorithms are more suitable for SVM classification compared to those from the LDA *** convergence analysis for the authors proposed algorithms are also ***,the authors conduct experiments on various machine learning data sets to evaluate the *** experiment results show that the authors’algorithms perform significantly better than other algorithms,which indicates their superior abilities on classification tasks.

关键词： iterative methods machine leaning support vector machunes

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Intracranial Hemorrhage Segmentation with YOLO and an Uncertainty Rectified Segment Anything Model 4th

Weakly Supervised Intracranial Hemorrhage Segmentation with...

引用

4th International Workshop on Imaging and Treatment Challenges, SWITCH 2024, and 6th International Challenge on Ischemic Stroke Lesion Segmentation Challenge, ISLES 2024, Held in Conjunction with Medical Image Computing and computer Assisted Intervention, MICCAI 2024

作者： Spiegler, Pascal Rasoulian, Amirhossein Xiao, Yiming Department of Computer Science and Software Engineering Concordia University Montreal Canada NeuroRx Research Montreal Canada

ISBN: (纸本)9783031811005

Intracranial hemorrhage (ICH) is a life-threatening condition that requires rapid and accurate diagnosis to improve treatment outcomes and patient survival rates. Recent advancements in supervised deep learning have greatly improved the analysis of medical images, but often rely on extensive datasets with high-quality annotations, which are costly, time-consuming, and require medical expertise to prepare. To mitigate the need for large amounts of expert-prepared segmentation data, we have developed a novel weakly supervised ICH segmentation method that utilizes the YOLO object detection model and an uncertainty-rectified Segment Anything Model (SAM). In addition, we have proposed a novel point prompt generator for this model to further improve segmentation results with YOLO-predicted bounding box prompts. Our approach achieved a high accuracy of 0.933 and an AUC of 0.796 in ICH detection, along with a mean Dice score of 0.629 for ICH segmentation, outperforming existing weakly supervised and popular supervised (UNet and Swin-UNETR) approaches. Overall, the proposed method provides a robust and accurate alternative to the more commonly used supervised techniques for ICH quantification without requiring refined segmentation ground truths during model training. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Binary Program Vulnerability Mining Based on Neural Network

引用

computers, Materials & Continua 2024年第2期78卷 1861-1879页

作者： Zhenhui Li Shuangping Xing Lin Yu Huiping Li Fan Zhou Guangqiang Yin Xikai Tang Zhiguo Wang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu611731China School of Electrical and Computer Engineering University ofWaterlooWaterlooN2L 3G1Canada

software security analysts typically only have access to the executable program and cannot directly access the source code of the *** poses significant challenges to security *** it is crucial to identify vulnerabilities in such non-source code programs,there exists a limited set of generalized tools due to the low versatility of current vulnerability mining ***,these tools suffer from some *** terms of targeted fuzzing,the path searching for target points is not streamlined enough,and the completely random testing leads to an excessively large search ***,when it comes to code similarity analysis,there are issues with incomplete code feature extraction,which may result in information *** this paper,we propose a cross-platform and cross-architecture approach to exploit vulnerabilities using neural network obfuscation *** leveraging the Angr framework,a deobfuscation technique is introduced,along with the adoption of a VEX-IR-based intermediate language conversion *** combination allows for the unified handling of binary programs across various architectures,compilers,and compilation ***,binary programs are processed to extract multi-level spatial features using a combination of a skip-gram model with self-attention mechanism and a bidirectional Long Short-Term Memory(LSTM)***,the graph embedding network is utilized to evaluate the similarity of program *** on these similarity scores,a target function is determined,and symbolic execution is applied to solve the target *** solved content serves as the initial seed for targeted *** binary program is processed by using the de-obfuscation technique and intermediate language transformation method,and then the similarity of program functions is evaluated by using a graph embedding network,and symbolic execution is performed based on these similarity *** approach facilitates

关键词： Vulnerability mining de-obfuscation neural network graph embedding network symbolic execution

来源：评论

学校读者我要写书评

暂无评论

Motif-oriented influence maximization for viral marketing in large-scale social networks 38

Motif-oriented influence maximization for viral marketing in...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhou, Mingyang Cao, Weiji Liao, Hao Mao, Rui Guangdong Province Key Laboratory of Popular High Performance Computers College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

The influence maximization (IM) problem aims to identify a budgeted set of nodes with the highest potential to influence the largest number of users in a cascade model, a key challenge in viral marketing. Traditional IM approaches consider each user/node independently as a potential target customer. However, in many scenarios, the target customers comprise motifs, where activating only one or a few users within a motif is insufficient for effective viral marketing, which, nevertheless, receives little attention. For instance, if a motif of three friends planning to dine together, targeting all three simultaneously is crucial for a restaurant advertisement to succeed. In this paper, we address the motif-oriented influence maximization problem under the linear threshold model. We prove that the motif-oriented IM problem is NP-hard and that the influence function is neither supermodular nor submodular, in contrast to the classical IM setting. To simplify the problem, we establish the submodular upper and lower bounds for the influence function. By leveraging the submodular property, we propose a natural greedy strategy that simultaneously maximizes both bounds. Our algorithm has an approximation ratio of τ·(1−1/e−Ε) and a near-linear time complexity of O((k+l)(m+η) log η/Ε2). Experimental results on diverse datasets confirm the effectiveness of our approach in motif maximization. © 2024 Neural information processing systems foundation. All rights reserved.

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：