检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

2,959 篇 会议
39 篇 期刊文献
7 册 图书

馆藏范围

3,005 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,760 篇 工学
- 1,407 篇 计算机科学与技术...
- 684 篇 软件工程
- 490 篇 电气工程
- 397 篇 信息与通信工程
- 203 篇 控制科学与工程
- 130 篇 生物工程
- 79 篇 电子科学与技术（可...
- 65 篇 生物医学工程（可授...
- 59 篇 机械工程
- 54 篇 仪器科学与技术
- 49 篇 光学工程
- 34 篇 网络空间安全
- 30 篇 动力工程及工程热...
- 24 篇 材料科学与工程（可...
- 24 篇 安全科学与工程
- 22 篇 化学工程与技术
- 20 篇 测绘科学与技术
- 19 篇 石油与天然气工程
517 篇 理学
- 226 篇 物理学
- 190 篇 数学
- 143 篇 生物学
- 58 篇 统计学（可授理学、...
- 40 篇 系统科学
- 27 篇 化学
203 篇 管理学
- 135 篇 管理科学与工程(可...
- 81 篇 图书情报与档案管...
- 31 篇 工商管理
135 篇 医学
- 112 篇 临床医学
- 38 篇 基础医学(可授医学...
37 篇 法学
- 20 篇 社会学
18 篇 文学
14 篇 农学
10 篇 教育学
9 篇 经济学
2 篇 军事学

主题

590 篇 neural networks
173 篇 training
168 篇 artificial neura...
165 篇 deep learning
135 篇 computational mo...
124 篇 feature extracti...
115 篇 neural network
114 篇 convolutional ne...
88 篇 machine learning
87 篇 neurons
86 篇 parallel process...
79 篇 deep neural netw...
74 篇 computer archite...
73 篇 distributed comp...
65 篇 signal processin...
62 篇 distributed proc...
62 篇 accuracy
60 篇 recurrent neural...
55 篇 data models
50 篇 convolutional ne...

机构

11 篇 institute of inf...
9 篇 school of cyber ...
8 篇 univ chinese aca...
8 篇 natl univ def te...
7 篇 college of compu...
7 篇 carnegie mellon ...
7 篇 national laborat...
7 篇 beijing universi...
7 篇 natl univ def te...
6 篇 shanghai jiao to...
6 篇 the islamic univ...
6 篇 department of co...
5 篇 science and tech...
5 篇 ibm tj watson re...
5 篇 school of inform...
5 篇 king saud univer...
5 篇 shandong normal ...
5 篇 kaust thuwal
5 篇 university of ch...
5 篇 natl univ def te...

作者

8 篇 li dongsheng
8 篇 dou yong
8 篇 jie liu
6 篇 richtarik peter
6 篇 ribeiro alejandr...
6 篇 liu jie
6 篇 niu xin
6 篇 yong dou
6 篇 shulian yang
6 篇 zhang wei
5 篇 ryabinin max
5 篇 segarra santiago
5 篇 lai zhiquan
5 篇 ding bo
5 篇 qiao peng
5 篇 xu jiren
5 篇 kokkinos yiannis
5 篇 peng yuxing
5 篇 wang huaimin
5 篇 li aiping

语言

2,925 篇 英文
72 篇 其他
8 篇 中文
2 篇 土耳其文

检索条件"任意字段=Conference on Neural Network and Distributed Processing"

共 3005 条记录，以下是1081-1090 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Evaluation of MPI Allreduce for distributed Training of Convolutional neural networks

Evaluation of MPI Allreduce for Distributed Training of Conv...

引用

Euromicro conference on Parallel, distributed and network-Based processing

作者： Adrián Castelló Mar Catalán Manuel F. Dolz José I. Mestre Enrique S. Quintana-Ortí José Duato Universitat Jaume I Castellón Spain Universitat Politècnica de València Valencia Spain

Training deep neural networks is a costly procedure, often performed via sophisticated deep learning frameworks on clusters of computers. As faster processor technologies are integrated into these cluster facilities (e.g., NVIDIA's graphics accelerators or Google's tensor processing units), the communication component of the training process rapidly becomes a performance bottleneck. In this paper, we offer a complete analysis of the key collective communication primitive for the distributed data-parallel training of convolutional network networks (CNNs) focused on three relevant instances of the Message Passing Interface (MPI): MPICH, OpenMPI, and IntelMPI. In addition, our experimental evaluation is extended to expose the practical impact of this collective primitive when the training is performed using TensorFlow+ Horovod on a 16-node cluster. Finally, the theoretical analysis is further refined to a number of accelerated cluster configurations that are emulated by adjusting the communication-arithmetic ratio of the training process.

关键词： Training Graphics Deep learning Tensors Message passing neural networks Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

TripleBlind: A Privacy-Preserving Framework for Decentralized Data and Algorithms 35

TripleBlind: A Privacy-Preserving Framework for Decentralize...

引用

35th Annual conference on neural Information processing Systems (NeurIPS)

作者： Gharibi, Gharib Gilkalaye, Babak Poorebrahim Patel, Ravi Rademacher, Andrew Wagner, David Fay, Jack Moore, Gary Penrod, Steve Storm, Greg Das, Riddhiman TripleBlind Inc Kansas City MO 64112 USA

Centralized sharing of sensitive data for training and inference is challenging and undesired due to privacy, competition, and legal concerns. While distributed learning and secure inference have demonstrated significant privacy gains, these methods still largely ignore the design and implementation of practical, privacy-preserving tool support. To address these challenges, we present TripleBlind, an automated privacy-preserving framework for creating and consuming data-driven applications from decentralized data and algorithms. TripleBlind provides a set of automated, high-level APIs that enable (1) extracting knowledge from remote data without moving it outside the owner's infrastructure, (2) training AI models from decentralized data, and (3) consuming trained models for secure inference-as-a-service;all without compromising the privacy of either the model/query or the data. In this short paper, we shed light on the underlying training and inference methods, the design and implementation of our framework, and showcase the actual code necessary to run a secure, remote inference using our secure multi-party computation API. A video demo highlighting the main features of our framework is located at ***/neurips2021

关键词： Machine learning deep learning privacy distributed learning secure multi-party computation inference-as-a-service

来源：评论

学校读者我要写书评

暂无评论

A motorcyclist helmet detection system through a two-stage CNN approach

A motorcyclist helmet detection system through a two-stage C...

引用

IEEE Chilean conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON)

作者： Alfonso, Ricardo Daher, Christian Arzamendia, Mario Cikel, Kevin Gregor, Derlis Gutierrez, Daniel Toral, Sergio Villagra, Marcos Natl Univ Asuncion FIUNA Fac Engn Lab Distributed Syst LSD San Lorenzo Paraguay Univ Seville Higher Tech Sch Engn Dept Elect Engn Seville Spain

ISBN: (纸本)9781665408738

Motorcyclists are the road users more prone to suffer from traffic accidents and serious injuries. The effects of accidents can be alleviated by a suitable use of helmets that helps to protect a motorcyclist's head. This paper presents a tool for facilitating the recognition of motorcyclists who circulate in public roads without wearing helmets. This tool can help local authorities to quantify the compliance levels of motorcyclists and prevent irreversible damage to them. The proposed system of this work was developed using image processing and convolutional neural networks (CNN), which combined a pre-trained model of SSD Mobilenet V2 for the detection of motorcycles followed by a custom made model for helmet detection. The automated tool was implemented using an NVIDIA Jetson TX2 board. Results show a precision of 95% for the detection of motorcyclists and 93% for the classification of motorcyclists with and without a protective helmet.

关键词： Computer vision Convolutional neural networks Deep learning Helmet detection

来源：评论

学校读者我要写书评

暂无评论

Analysis of Smart City Sustainability Based on Big Data Integrated Edge Computing Modeling with neural network

Analysis of Smart City Sustainability Based on Big Data Inte...

引用

Smart Systems for Electrical, Electronics, Communication and Computer Engineering (ICSSEECC), International conference on

作者： Sarah Ali Abdulkareem Zahraa N.Abdulhussain Ragheed Hussam Khaled Farhan Mohammed Al-Farouni Computer Technologies Engineering Al-Turath University College Baghdad Iraq Department of Medical Devices Engineering Technologies National University of Science and Technology Dhi Qar Nasiriyah Iraq Technical Computer Engineering Department Al-Kunooze University College Basrah Iraq Department of Computer Engineering Technologies Al-Kitab University Kirkuk Iraq Department of computers Techniques engineering College of technical engineering The Islamic university Najaf Iraq

ISBN: (数字)9798350378177

ISBN: (纸本)9798350378184

The fact that urban areas are preferred places to live is evidence of a sophisticated system in which authorities can effectively satisfy citizens' needs and address economic, social, and environmental sustainability issues while facing several obstacles. The smart city idea improves sustainable development, human flourishing, and economic expansion. The smart city concept can potentially enhance a wide range of municipal operations, including transportation, energy, and healthcare, education, and resource management. Many network quality, stability, and security issues have arisen from developing smart cities and IoT applications. The dispersed nature of smart cities and IoT technology has led to problems with service reliability, longevity, and safety. This paper proposes Big Data Integrated Edge Computing Modeling (BDIECM) to improve data management interfaces' security and sustainability elements in various smart city applications to eliminate hazards. Edge computing allows for distributed processing and communication, useful in various contexts, including intelligent transportation systems, health and social services. Edge computing's ability to reduce latency is particularly useful for mission-critical applications. The system coordinates between dispersed edge servers and security mediator nodes for smart city use cases. The simulation results validate the suggested approach can significantly enhance the security ratio of95.2%, sustainability ratio of94.1 %,reliability ratio of 91.4 %, scalability ratio of 93.5 %, latency ratio of 21.1 %, and data transmission ratio of 96.2 % compared to other methods.

关键词： Smart cities Computational modeling Scalability Computer architecture Big Data Data models Security

来源：评论

学校读者我要写书评

暂无评论

UNCERTAINTY QUANTIFICATION FOR REMAINING USEFUL LIFETIME PREDICTION WITH MULTI-CHANNEL SENSORY DATA

UNCERTAINTY QUANTIFICATION FOR REMAINING USEFUL LIFETIME PRE...

引用

IEEE International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Deng, Yingjun Wu, Huaming Jiang, Chao Tianjin Univ Ctr Appl Math Tianjin 300072 Peoples R China Sci & Technol Particle Transportand Seperat Lab Tianjin 300180 Peoples R China

ISBN: (纸本)9781509066315

For remaining useful lifetime (RUL) prediction with multi-channel sensory data, long-term prediction has more uncertainty than short-term prediction. In this paper, the ratio of mean to variance was considered to measure the uncertainty propagation rate (UPR) of RUL prediction over time. Furthermore, we use a recurrent neural network (RNN) as the linking function for the mean of inverse Gaussian distributed RUL to construct a two-stage hybrid model. Later the RNN and the UPR are jointly trained with sensory data and failure records via alternating minimization. Proposed algorithms are validated in a simulation test.

关键词： Remaining useful lifetime uncertainty propagation rate recurrent neural network linking function generalized linear model

来源：评论

学校读者我要写书评

暂无评论

A lightweight approach to two-person interaction classification in sparse image sequences

A lightweight approach to two-person interaction classificat...

引用

Federated conference on Computer Science and Information Systems (FedCSIS)

作者： Włodzimierz Kasprzak Paweł Piwowarski Van-Khanh Do Institute of Control and Computation Eng. Warsaw University of Technology Warszawa Poland

ISBN: (数字)9788396242396

ISBN: (纸本)9781665407335

A lightweight neural network-based approach to two-person interaction classification in image sequences, based on human skeletons detected in sparse video frames, is proposed. The idea is to use an ensemble of pose classifiers ("experts"), where every expert is trained on different time-indexed snapshots of an interaction. Thus, the expertise of "weak" classifiers is distributed over the time duration of an interaction. The overall classification result is a weighted combination of all the pose experts. Important element of proposed solution is the refinement of skeleton data, based on a merging-of-joints procedure. This allows the generation of reliable features being passed to the artificial neural network. This is the key to our lightweight solution, as ANN resources, needed for feature space transformation, can be significantly limited. Our network model was trained and tested on the interaction subset of the well-known NTU RGB+D dataset, although only 2D skeleton information is used, typical in video analysis. The test results show comparable performance of our method with some of the best so far reported STM- and CNN-based classifiers for this dataset, when they process sparse frame sequences, like we did. The recently proposed multi-stream Graph CNNs have shown superior results but only when processing dense frame sequences. Considering the dominating processing time and resources needed for skeleton estimation in every frame of the sequence, the key to real-time interaction recognition is to limit the number of processed frames.

关键词： Computer science Estimation Artificial neural networks Skeleton Real-time systems Libraries Image sequences

来源：评论

学校读者我要写书评

暂无评论

DETECT INSIDER ATTACKS USING CNN IN DECENTRALIZED OPTIMIZATION

DETECT INSIDER ATTACKS USING CNN IN DECENTRALIZED OPTIMIZATI...

引用

IEEE International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Li, Gangqiang Wu, Sissi Xiaoxiao Zhang, Shengli Li, Qiang Shenzhen Univ Coll Elect & Informat Engn Shenzhen Peoples R China Univ Elect Sci & Technol China Sch Info & Commun Engn Chengdu Peoples R China Peng Cheng Lab Shenzhen Peoples R China

ISBN: (纸本)9781509066315

This paper studies the security issue of a gossip-based distributed projected gradient (DPG) algorithm, when it is applied for solving a decentralized multi-agent optimization. It is known that the gossip-based DPG algorithm is vulnerable to insider attacks because each agent locally estimates its (sub)gradient without any supervision. This work leverages the convolutional neural network (CNN) to perform the detection and localization of the insider attackers. Compared to the previous work, CNN can learn appropriate decision functions from the original state information without preprocessing through artificially designed rules, thereby alleviating the dependence on complex pre-designed models. Simulation results demonstrate that the proposed CNN-based approach can effectively improve the performance of detecting and localizing malicious agents, as compared with the conventional pre-designed score-based model.

关键词： distributed optimization gossip algorithms insider attack convolutional neural network (CNN)

来源：评论

学校读者我要写书评

暂无评论

A UAV Swarm Sensing Oriented distributed Computing Cooperation Scheme 6

A UAV Swarm Sensing Oriented Distributed Computing Cooperati...

引用

6th IEEE International conference on Computer and Communication Systems, ICCCS 2021

作者： Li, Tianyang Cheng, Zekun Leng, Supeng School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9780738126043

With the advantages of flexibility and miniaturization, Unmanned Aerial Vehicle (UAV) has been widely applied to operate sensing tasks in many complicated environments. Based on the airborne sensors, a UAV can capture multiple videos or snapshots for monitoring and data analysis. However, the scarce computing resource of one single UAV may cause an unacceptable execution delay for image processing, especially when a batch of images are captured in a very short period of time. To solve the challenge, we propose a UAV swarm based distributed computing collaboration structure to integrate the computing resource of UAVs for real-time sensing tasks. Specifically, a UAV is elected as the coordinator to conduct the resource scheduling strategy for the computing cooperation among the remaining UAVs. In order to improve the utilization of computing resource, different layers of the Convolutional neural network (CNN) are computed by diverse UAVs. These UAVs can rapidly process the batch of images in a pipeline manner. Moreover, we formulate a non-linear programming model to minimize the batch execution time. A distributed CNN based Resource Scheduling (DCRS) algorithm is proposed to obtain the minimal execution time based on deep reinforcement learning. Simulation results demonstrate that our schemes not only can reduce the execution time but also can improve the computing resource utilization significantly. © 2021 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

An Optimizing E-govenment Model for Data Sharing via distributed Ledgers

An Optimizing E-govenment Model for Data Sharing via Distrib...

引用

Artificial Intelligence, Information processing and Cloud Computing (AIIPCC), International conference on

作者： Sheng Peng Linkai Zhu Jiadong Lu Renhui Tian Shiyang Song Wennan Wang Academy of Management Guangdong University of Science and Technology Zhuhai Yingying Technology Co. Ltd. Dongguan China Information Technology School Hebei University of Economics and Business Shijiazhuang China Alibaba Cloud Big Data Application College Zhuhai College of Science and Technology Zhuhai China “Institute of Data Science City University of Macau Macau China Academy of Management Guangdong University of Science and Technology Dongguan China

With the development of terminal technology and the expansion of application areas, the value of e-government applications and service requirements continue to increase. To develop and apply e-government, data sharing efficiency is essential. Using the e-government data sharing as a research object, a blockchain-based method is developed for optimizing data transfer. Blockchain technology is used for storing and delivering distributed data. Rather than distributing data nodes randomly, our network scenario model employs a matrix lattice model based on a complete undirected graph. Dual optimization is then applied to solve the problem. In order to find the optimal solution, a mathematical model and an artificial neural network are developed. To verify the performance and packet loss rate of the government data transmission method, a case study is conducted. Data Sharing is optimized to increase the lifetime of static aggregation nodes by at least 30% and lifetime of static aggregation nodes by at least 20%. The network lifetime can be extended by optimizing static aggregation nodes. Furthermore,it effectively improves the robustness.

关键词： Energy consumption Optimization methods Packet loss Data transfer Data models Mathematical models Robustness

来源：评论

学校读者我要写书评

暂无评论

Towards Finite-Time Consensus with Graph Convolutional neural networks

Towards Finite-Time Consensus with Graph Convolutional Neura...

引用

European Signal processing conference (EUSIPCO)

作者： Bianca Iancu Elvin Isufi Delft University of Technology Delft The Netherlands

ISBN: (数字)9789082797053

ISBN: (纸本)9781728150017

This work proposes a learning framework for distributed finite-time consensus with graph convolutional neural networks (GCNNs). Consensus is a central problem in distributed and adaptive optimisation, signal processing, and control. We leverage the link between finite-time consensus and graph filters, and between graph filters and GCNNs to study the potential of a readily distributed architecture for reaching consensus. We have found GCNNs outperform classical graph filters for distributed consensus and generalize better to unseen topologies such as distributed networks affected by link losses.

关键词： network topology Convolution neural networks Europe Topology Convolutional neural networks Optimization

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共301页 << < 105 106 107 108 109 110 111 112 113 114 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：