检索结果-内蒙古大学图书馆

REQUIRED NUMBER OF ITERATIONS FOR SPARSE SIGNAL RECOVERY VIA ORTHOGONAL LEAST SQUARES

Journal of Computational Mathematics 2023年第1期41卷 1-17页

作者： Haifeng Li Jing Zhang Jinming Wen Dongfang Li Henan Engineering Laboratory for Big Data Statistical Analysis and Optimal Control College of Mathematics and Information ScienceHenan Normal UniversityXinxiang 453007China College of Information Science and Technology Jinan UniversityGuangzhou 510632China School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and TechnologyWuhan 430074China

In countless applications,we need to reconstruct a K-sparse signal x∈R n from noisy measurements y=Φx+v,whereΦ∈R^(m×n)is a sensing matrix and v∈R m is a noise *** least squares(OLS),which selects at each step the column that results in the most significant decrease in the residual power,is one of the most popular sparse recovery *** this paper,we investigate the number of iterations required for recovering x with the OLS *** show that OLS provides a stable reconstruction of all K-sparse signals x in[2.8K]iterations provided thatΦsatisfies the restricted isometry property(RIP).Our result provides a better recovery bound and fewer number of required iterations than those proposed by Foucart in 2013.

关键词： Sparse signal recovery Orthogonal least squares(OLS) Restricted isometry property(RIP)

来源：评论

学校读者我要写书评

暂无评论

Representation learning: serial-autoencoder for personalized recommendation

引用

Frontiers of Computer science 2024年第4期18卷 61-72页

作者： Yi ZHU Yishuai GENG Yun LI Jipeng QIANG Xindong WU School of Information Engineering Yangzhou UniversityYangzhou 225127China Key Laboratory of Knowledge Engineering with Big Data(Ministry of Education of the People’s Republic of China) Hefei University of TechnologyHefei 230009China School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China

Nowadays,the personalized recommendation has become a research hotspot for addressing information *** this,generating effective recommendations from sparse data remains a ***,auxiliary information has been widely used to address data sparsity,but most models using auxiliary information are linear and have limited *** to the advantages of feature extraction and no-label requirements,autoencoder-based methods have become quite ***,most existing autoencoder-based methods discard the reconstruction of auxiliary information,which poses huge challenges for better representation learning and model *** address these problems,we propose Serial-Autoencoder for Personalized Recommendation(SAPR),which aims to reduce the loss of critical information and enhance the learning of feature ***,we first combine the original rating matrix and item attribute features and feed them into the first autoencoder for generating a higher-level representation of the ***,we use a second autoencoder to enhance the reconstruction of the data representation of the prediciton rating *** output rating information is used for recommendation *** experiments on the MovieTweetings and MovieLens datasets have verified the effectiveness of SAPR compared to state-of-the-art models.

关键词： personalized recommendation autoencoder representation learning collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

A Survey of LLM datasets:From Autoregressive Model to AI Chatbot

引用

Journal of Computer science & technology 2024年第3期39卷 542-566页

作者：杜非马新建杨婧如柳熠罗超然王学斌姜海鸥景翔 National Key Laboratory of Data Space Technology and System Beijing 100195China Advanced Institute of Big Data Beijing 100195China Fu Foundation School of Engineering and Applied Science Columbia UniversityNY 10027U.S.A. School of Software and Microelectronics Peking UniversityBeijing 100091China CCF IEEE

Since OpenAI opened access to ChatGPT,large language models(LLMs)become an increasingly popular topic attracting researchers’attention from abundant ***,public researchers meet some problems when developing LLMs given that most of the LLMs are produced by industries and the training details are typically *** datasets are an important setup of LLMs,this paper does a holistic survey on the training datasets used in both the pre-train and fine-tune *** paper first summarizes 16 pre-train datasets and 16 fine-tune datasets used in the state-of-the-art ***,based on the properties of the pre-train and fine-tune processes,it comments on pre-train datasets from quality,quantity,and relation with models,and comments on fine-tune datasets from quality,quantity,and *** study then critically figures out the problems and research trends that exist in current LLM *** study helps public researchers train and investigate LLMs by visual cases and provides useful comments to the research community regarding data *** the best of our knowledge,this paper is the first to summarize and discuss datasets used in both autoregressive and chat *** survey offers insights and suggestions to researchers and LLM developers as they build their models,and contributes to the LLM study by pointing out the existing problems of LLM studies from the perspective of data.

关键词： large language model(LLM) autoregressive model AI chatbot natural language processing(NLP)corpora OpenAI

来源：评论

学校读者我要写书评

暂无评论

Steel surface Defect Detection Algorithm Based on Improved YOLOv5s 6

Steel surface Defect Detection Algorithm Based on Improved Y...

引用

6th IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2024

作者： Su, Yingying Deng, Yuanyuan Zhou, Nengyang Si, Hongyun Peng, Jie Chongqing University of Science and Technology College of Electrical Engineering Chongqing China Chongqing Key Laboratory of Public Big Data Security Technology Chongqing China

ISBN: (纸本)9798350316520

To address challenges in steel surface defect detection, such as low accuracy and slow processing speed, an enhanced algorithm is proposed. The C3 module is replaced with GSConv (multi-channel shuffle convolution) to improve parameter efficiency and detection accuracy. The nearest neighbor up-sampling is substituted with CARAFE (a lightweight operator) to enhance the receptive field and utilize semantic information. GhostNetV2 replaces the CBS convolutional module for efficient feature extraction through stacking operations. Additionally, the Hard Swish activation function is incorporated to boost accuracy. Experimental results on the NEU-DET dataset demonstrate that the average accuracy of the improved YOLOv5s algorithm is 81.2%, a 1.7% increase compared to the original algorithm, the amount of computation is 17.2GFLOPs and the number of model parameters is 8.65M. The model effectively enhances detection accuracy. © 2024 IEEE.

关键词： Surface defects

来源：评论

学校读者我要写书评

暂无评论

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need 38

Unlearnable 3D Point Clouds: Class-wise Transformation Is Al...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC. © 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

Differentially Private Federated Stochastic Primal-Dual Learning for Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第11期12卷 17034-17050页

作者： Li, Yiwei Wang, Shuai Chang, Tsung-Hui Xiamen University of Technology Fujian Key Laboratory of Communication Network and Information Processing Xiamen361024 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China Chinese University of Hon g Kong School of Science and Engineering Shenzhen518172 China Shenzhen Research Institute of Big Data Shenzhen518172 China

Federated learning (FL) has the potential to empower Internet of Vehicles (IoV) networks by enabling smart vehicles (SVs) to participate in the learning process under the orchestration of a vehicular service provider while keeping data locally. In this article, we propose a novel federated stochastic primal-dual algorithm with differential privacy (FedSPD-DP) to ensure robust privacy protection for FL based IoV (FL-IoV) systems. The FedSPD-DP algorithm leverages multiple steps of local stochastic gradient descent (SGD) and partial client participation (PCP) to improve communication efficiency while incorporating differential privacy (DP) to ensure privacy protection. Our theoretical analysis explores the impact of these strategies on learning performance. Specifically, we demonstrate that the data sampling strategy and PCP enhance data privacy, while a larger number of local SGD steps may increase privacy leakage, revealing a nontrivial tradeoff between communication efficiency and privacy protection. Extensive experiments on real-world data validate the effectiveness of the proposed algorithm, showing superior performance compared to state-of-the-art FL algorithms, and confirming the analytical results and properties. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Facile synthesis of W-Mo bimetallic oxides with high adsorption properties from secondary resources

引用

Tungsten 2024年第4期6卷 806-820页

作者： Jia-Li Cheng Yang-Si Liu Xiao-Li Xi Zuo-Ren Nie Collaborative Innovation Center of Capital Resource-Recycling Material Technology College of Materials Science and EngineeringBeijing University of TechnologyBeijing100124China National Engineering Laboratory for Industrial Big-Data Application Technology Beijing University of TechnologyBeijing100124China Key Laboratory of Advanced Functional Materials Ministry of EducationBeijing University of TechnologyBeijing100124China

A simple solvothermal method was used to obtain W-Mo bimetallic oxides from W-Mo alloy scrap,and pure metal powders were also used as the raw materials to simulate *** products had a sea urchin-like structure with abundant oxygen vacancies and the products prepared at low temperatures forms a sosoloid resembling orthorhombic W_(0.4)Mo_(0.6)O_(3).The WMo bimetallic oxide prepared at the reaction temperature of 120℃exhibited excellent selective adsorption performance for methylene blue(MB),which the adsorption rate of MB reached 99%in 12 min and the adsorption rate reached 90%after6 adsorption *** the W-Mo molar ratio is 1:3,the maximum adsorption capacity of sample for MB can reach1148 mg·g^(-1).The adsorption process followed the Langmuir and pseudo-second-order models,which is surface-controlled monolayer *** experimental results show the feasibility of preparing W-Mo bimetal oxide products from pure materials and *** process is simple and effective,which offered a potential approach for secondary resource recycling and reusing.

关键词： W-Mo bimetallic oxide Oxygen vacancy Selective adsorption W-Mo alloy scrap Solvothermal

来源：评论

学校读者我要写书评

暂无评论

PAB-Mamba-YOLO:VSSM assists in YOLO for aggressive behavior detection among weaned piglets

引用

Artificial Intelligence in Agriculture 2025年第1期15卷 52-66页

作者： Xue Xia Ning Zhang Zhibin Guan Xin Chai Shixin Ma Xiujuan Chai Tan Sun Agricultural Information Institute Chinese Academy of Agricultural SciencesBeijing 100081China Key Laboratory of Agricultural Big Data Ministry of Agriculture and Rural AffairsBeijing 100081China School of Information Science and Technology Beijing Forestry UniversityBeijing 100083China

Aggressive behavior among piglets is considered a harmful social *** weaned piglets with intense aggressive behaviors is paramount for pig breeding *** study introduced a novel hybrid model,PAB-Mamba-YOLO,integrating the principles of Mamba and YOLO for efficient visual detection of weaned piglets'aggressive behaviors,including climbing body,nose hitting,biting tail and biting *** the proposed model,a novel CSPVSS module,which integrated the Cross Stage Partial(CSP)structure with the Visual State Space Model(VSSM),has been *** module was adeptly integrated into the Neck part of the network,where it harnessed convolutional capabilities for local feature extraction and leveraged the visual state space to reveal long-distance *** model exhibited sound performance in detecting aggressive behaviors,with an average precision(AP)of 0.976 for climbing body,0.994 for nose hitting,0.977 for biting tail and 0.994 for biting *** mean average precision(mAP)of 0.985 reflected the model's overall effectiveness in detecting all classes of aggressive *** model achieved a detection speed FPS of 69 f/s,with model complexity measured by 7.2 G floating-point operations(GFLOPs)and parameters(Params)of 2.63 *** experiments with existing prevailing models confirmed the superiority of the proposed *** work is expected to contribute a glimmer of fresh ideas and inspiration to the research field of precision breeding and behavioral analysis of animals.

关键词： Aggressive behaviors Weaned piglet Mamba YOLO Hybrid detection model

来源：评论

学校读者我要写书评

暂无评论

CoRE:Constrained Robustness Evaluation of Machine Learning-Based Stability Assessment for Power Systems

引用

IEEE/CAA Journal of Automatica Sinica 2023年第2期10卷 557-559页

作者： Zhenyong Zhang David K.Y.Yau the State Key Laboratory of Public Big Data and the College of Computer Science and Technology Guizhou UniversityGuiyang 550025China IEEE the Pillar of Information Systems Technology and Design Singapore University of Technology and DesignSingapore 487372Singapore

Dear Editor,Machine learning(ML) approaches have been widely employed to enable real-time ML-based stability assessment(MLSA) of largescale automated electricity grids. However, the vulnerability of MLSA to malicious cyber-attacks may lead to wrong decisions in operating the physical grid if its resilience properties are not well understood before deployment. Unlike adversarial ML in prior domains such as image processing, specific constraints of power systems that the attacker must obey in constructing adversarial samples require new research on MLSA vulnerability analysis for power systems.

关键词： enable constraints Power

来源：评论

学校读者我要写书评

暂无评论

Group-wise co-salient object detection via multi-view self-labeling novel class discovery

引用

Frontiers of Computer science 2024年第2期18卷 259-261页

作者： Yang WU Gang DONG Lingyan LIANG Yaqian ZHAO Kaihua ZHANG Inspur Electronic Information Industry Co. Ltd.Beijing 100080China Jiangsu Key Laboratory of Big Data Analysis Technology and Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and TechnologyNanjing 210044China

1 Introduction Co-salient object detection(CoSOD)aims to extract the salient object(s)that are common across a group of relevant images[1].Group-wise clue plays a crucial role in accurately predicting the co-salient ***,numerous groupwise deep models have been proposed by exploring consistency across images in unsupervised clustering manners[2-4]or the semantic connections guidance information[5].

关键词： consistency Group semantic

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：