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

2,958 篇 会议
39 篇 期刊文献
7 册 图书

馆藏范围

3,004 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,759 篇 工学
- 1,406 篇 计算机科学与技术...
- 685 篇 软件工程
- 489 篇 电气工程
- 396 篇 信息与通信工程
- 202 篇 控制科学与工程
- 130 篇 生物工程
- 78 篇 电子科学与技术（可...
- 65 篇 生物医学工程（可授...
- 58 篇 机械工程
- 54 篇 仪器科学与技术
- 49 篇 光学工程
- 33 篇 网络空间安全
- 30 篇 动力工程及工程热...
- 24 篇 安全科学与工程
- 23 篇 材料科学与工程（可...
- 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
516 篇 理学
- 225 篇 物理学
- 189 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
167 篇 artificial neura...
164 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
49 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
71 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 3004 条记录，以下是1381-1390 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：

On Realizing distributed Deep neural networks: An Astrophysics Case Study 27

On Realizing Distributed Deep Neural Networks: An Astrophysi...

引用

27th European Signal processing conference (EUSIPCO)

作者： Aspri, Maria Tsagkatakis, Grigorios Panousopoulou, Athanasia Tsakalides, Panagiotis Fdn Res & Technol Hellas FORTH Inst Comp Sci Iraklion Greece Univ Crete Dept Comp Sci Iraklion 70013 Greece

ISBN: (纸本)9789082797039

Deep Learning architectures are extensively adopted as the core machine learning framework in both industry and academia. With large amounts of data at their disposal, these architectures can autonomously extract highly descriptive features for any type of input signals. However, the extensive volume of data combined with the demand for high computational resources, are introducing new challenges in terms of computing platforms. The work herein presented explores the performance of Deep Learning in the field of astrophysics, when conducted on a distributed environment. To set up such an environment, we capitalize on TensorFlowOnSpark, which combines both TensorFlow's dataflow graphs and Spark's cluster management. We report on the performance of a CPU cluster, considering both the number of training nodes and data distribution, while quantifying their effects via the metrics of training accuracy and training loss. Our results indicate that distribution has a positive impact on Deep Learning, since it accelerates our network's convergence for a given number of epochs. However, network traffic adds a significant amount of overhead, rendering it suitable for mostly very deep models or in big Data Analytics.

关键词： distributed Deep Learning Convolutional neural networks Spectroscopic Redshift Estimation

来源：评论

学校读者我要写书评

暂无评论

Communication-Efficient Decentralized Learning with Sparsification and Adaptive Peer Selection

Communication-Efficient Decentralized Learning with Sparsifi...

引用

International conference on distributed Computing Systems

作者： Zhenheng Tang Shaohuai Shi Xiaowen Chu Hong Kong Baptist University

ISBN: (数字)9781728170022

ISBN: (纸本)9781728170039

The increasing size of machine learning models, especially deep neural network models, can improve the model generalization capability. However, large models require more training data and more computing resources (such as GPU clusters) to train. In distributed training, the communication overhead of exchanging gradients or models among workers becomes a potential system bottleneck that limits the system scalability. Recently, many research works aim to reduce communication time of two types of distributed deep learning architectures, centralized and decentralized.

关键词： Training Computational modeling Scalability neural networks Training data Graphics processing units distributed computing

来源：评论

学校读者我要写书评

暂无评论

EasyDist: An End-to-End distributed Deep Learning Tool for Cloud 19

EasyDist: An End-to-End Distributed Deep Learning Tool for C...

引用

ACM India Joint International conference on Data Science and Management of Data (CoDS-COMAD)

作者： Natu, Varun Ghosh, Rahul Amer Express Big Data Labs New York NY 10281 USA

ISBN: (纸本)9781450362078

With the increasing number of artificial intelligence (AI) applications, complex neural network based modeling on large scale data is becoming quite common. Using distributed deep learning (DDL), a data scientist can harness the computational power of multiple graphics processing units (GPUs) spread across different machines and significantly reduce neural network training times. In this paper, we focus on a TensorFlow based distributed training approach, which, unfortunately, leaves the auxiliary modeling capabilities (e.g., resource deployment, data distribution, run-time control etc.) to user-discretion. Additionally, these training capabilities cannot be accessed directly through popular high-level interfaces such as Keras. As a result, the transition to DDL from a single node training setting involves a steep learning curve for data scientists. To bridge this gap, we present EasyDist, an end-to-end DDL tool that preserves the single-node programming model by leveraging distributed TensorFlow between a Keras interface and public Cloud infrastructure. EasyDist is model agnostic, i.e., any neural network model written in Keras can use EasyDist for distributed training. Internally, EasyDist incorporates resource deployment, data allocation, training orchestration and result aggregation within a clean abstraction which allows the data scientist to focus on model definition. Evaluation of EasyDist on publicly available benchmark datasets and models shows that the model accuracy is not compromised in any significant way while the training times can be reduced upto similar to 6-8x compared to single machine settings.

关键词： distributed Deep Learning Cloud neural networks Keras

来源：评论

学校读者我要写书评

暂无评论

Intelligent recognition of insulator video stream based on embedded edge computing

Intelligent recognition of insulator video stream based on e...

引用

22nd International Symposium on High Voltage Engineering (ISH 2021)

作者： Y Sun Y. Zhang S. Chen Y. Chen K. Sun State Grid Shandong Electric Power Research Institute Jinan People's Republic of China Department of Electrical Engine ering North China Electric Power University Beijing People's Republic of China

Traditional intelligent recognition algorithm models of insulators are large and mostly completed by back-end servers, with large data transmission volume, high power consumption and poor real-time performance at the front and rear ends. In this paper, a miniature SSD convolutional neural network model is designed to enable it to be deployed in embedded edge computing devices and to recognize video images of insulators. Firstly, the low-latitude Core convolution group subnetwork is used to replace the high-latitude VGG network to extract the shallow features of the insulator, and then the auxiliary feature extraction subnetwork is used to predict the target, so as to reduce the number of model parameters. The model weight files generated by the training were transplanted to the edge computing platform of Jetson nano equipped with vision sensor. OpenCV was used to extract frames from the video images captured by vision sensor every 1 ms and real-time recognition performance was compared under different video resolutions. Experimental results show that the scheme reduces data transmission and realizes low delay recognition. The average recognition frame rate of insulator video images is 16.8 FPS and 19.7 FPS respectively at 1280*720 and 640*480 resolutions. The recognition process is relatively smooth and the recognition accuracy can reach 91.53%. The energy consumption of the whole identification process is less than 5W, which is an order of magnitude lower than that of traditional servers.

关键词： computer vision distributed processing feature extraction image recognition image resolution image sensors insulators power engineering computing power grids video signal processing video streaming convolutional neural nets

来源：评论

学校读者我要写书评

暂无评论

Chinese Intelligent Systems conference, CISC 2019

Chinese Intelligent Systems Conference, CISC 2019

引用

Chinese Intelligent Systems conference, CISC 2019

ISBN: (纸本)9789813296978

The proceedings contain 240 papers. The special focus in this conference is on Chinese Intelligent Systems. The topics include: Research About Abrasion Surface Morphology of Warhead by Structure Function Method;accurate Image Recognition of Plant Diseases Based on Multiple Classifiers Integration;Adaptive Control of DC Servo Based on PID neural network;LQR-Based Optimal Leader-Following Consensus of Heterogeneous Multi-agent Systems;couple-Group Tracking Consensus for Non-linear Multi-agent Systems with Time-Delays;optimization Algorithm for Power Flow Calculation Using Graph Theory;A New Approach to Developing General Manipulator Control System Application Based on ROS;Fault-Tolerant Control Based on LPV-Robust Model Predictive Control for Hypersonic Vehicle;stability Analysis of Discrete-Time Stochastic Systems with Borel-Measurable Markov Jumps;An Improvement of PWPF in Reaction Control System of Hypersonic Vehicle;trajectory Tracking Control of Quadrotor Helicopters Based on Controlled Lagrangians;Design of Object Edge Detection System Based on FPGA;research on Location of Pulse-Diagnosis Point Based on Image processing;bursty Topic Detection Based on Bursty Term Detection and Filtration;formation Consistency Research of Multi-robot Systems with Leader-Following;a Method of Non-line-of-Sight Measurement and Location;an Adaptive Controller for Wheeled Mobile Robot Trajectory Tracking;real-Time Semantic Segmentation network for Edge Deployment;solution of distributed Optimal Control Protocol for Second-Order Multi-agent Systems;estimating the Diffusion Source in Complex networks with Sparse Modeling Method;the Design of an Intelligent Screw Extruder Control System Based on Fuzzy Control;tracking via Enhanced Context-Aware Correlation Filter;Optimization and Simulation of Fuzzy Control Based on SOA;a New Fixed-Wing Formation Control Algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Low Complexity Decentralized neural Net with Centralized Equivalence using Layer-wise Learning

A Low Complexity Decentralized Neural Net with Centralized E...

引用

International Joint conference on neural networks (IJCNN)

作者： Xinyue Liang Alireza M. Javid Mikael Skoglund Saikat Chatterjee School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

We design a low complexity decentralized learning algorithm to train a recently proposed large neural network in distributed processing nodes (workers). We assume the communication network between the workers is synchronized and can be modeled as a doubly-stochastic mixing matrix without having any master node. In our setup, the training data is distributed among the workers but is not shared in the training process due to privacy and security concerns. Using alternating-direction-method-of-multipliers (ADMM) along with a layer-wise convex optimization approach, we propose a decentralized learning algorithm which enjoys low computational complexity and communication cost among the workers. We show that it is possible to achieve equivalent learning performance as if the data is available in a single place. Finally, we experimentally illustrate the time complexity and convergence behavior of the algorithm.

关键词： Training Biological neural networks Communication networks Computational complexity Convex functions

来源：评论

学校读者我要写书评

暂无评论

Optimizing Secure Information Interaction in distributed Computing Systems by the Sequential Concessions Method

Optimizing Secure Information Interaction in Distributed Com...

引用

Euromicro conference on Parallel, distributed and network-Based processing

作者： Igor Kotenko Yury Sineshchuk Igor Saenko (SPIIRAS) St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences Saint-Petersburg University of the Ministry of Internal Affairs of the Russian Federation Saint-Petersburg Russia

ISBN: (数字)9781728165820

ISBN: (纸本)9781728165837

The paper proposes a new approach to multicriteria optimization of the structure of secure information interaction in distributed computing systems. A distinguishing feature of the approach is the use of the sequential concessions method. This approach provides the acceptable flexibility in comparing the system construction variants by taking into account not only the priority of the system according to efficiency indicators, but also the relationships of the indicators. The mathematical basis of the proposed method is considered. The procedure of implementation of the proposed method for ensuring security of information interaction in a distributed hierarchical automated control system is demonstrated, and its experimental assessment is given.

关键词： Artificial neural networks Computer networks Cyber-physical systems Optimization

来源：评论

学校读者我要写书评

暂无评论

Analyzing distributed Deep neural network Deployment on Edge and Cloud Nodes in IoT Systems

Analyzing Distributed Deep Neural Network Deployment on Edge...

引用

IEEE International conference on Edge Computing (EDGE)

作者： Majid Ashouri Fabian Lorig Paul Davidsson Romina Spalazzese Sergej Svorobej Internet of Things and People Research Center Malmö University Malmö Sweden School of Computer Science and Statistics Trinity College Dublin Dublin 2 Ireland

The following topics are dealt with: distributed processing; 5G mobile communication; production engineering computing; optimisation; mobile computing; resource allocation; cloud computing; learning (artificial intell... 详细信息

ISBN: (数字)9781728182544

ISBN: (纸本)9781728182551

关键词： Cloud computing Analytical models Computational modeling neural networks Analytic hierarchy process Tools Task analysis

来源：评论

学校读者我要写书评

暂无评论

MapReduce-Based BP neural network Classification of Aquaculture Water Quality

MapReduce-Based BP Neural Network Classification of Aquacult...

引用

Computer Information and Big Data Applications (CIBDA), International conference on

作者： Yan Wen Min Li Yu Ye Academy of Mechatronics and Information Chengdu China

ISBN: (数字)9781728198378

ISBN: (纸本)9781728198385

As information technology develops and prevails across the globe, the informatization and data processing efficiency in the aquaculture field are exerting increasing impact on the intelligent conversion of this field. The aquaculture water quality indicators were analyzed by a feedforward error back propagation algorithm (BP neural network) with strong nonlinear mapping capacity, and the complicated nonlinear relations among the parameters of the aquaculture environment were solved. An aquaculture element analysis model was proposed, the Johnson attribute reduction algorithm based on the discernibility matrix was used to optimize the traditional algorithm, and the network convergence speed was increased under a given accuracy. The MapReduece distributed programming model was then used to perform parallel design of the BP neural network algorithm to meet the needs of massive data processing in aquaculture platforms. Also, case studies were performed to analyze the aquaculture element model and the parallel learning algorithm, and the big data framework design and data analysis method are integrated to develop an efficient, fault-tolerant aquaculture data management, mining, visualization big data system.

关键词： neural networks Aquaculture Data analysis

来源：评论

学校读者我要写书评

暂无评论

Adaptive distributed video surveillance system

Adaptive distributed video surveillance system

引用

Technology and Entrepreneurship, (ICTE-V), International conference on

作者： Alexander Khelvas Darya Demyanova Alexander Gilya-Zetinov Egor Konyagin Roman Khafizov Ruslan Pashkov Center of Open Systems MIPT Dolgoprudnii Russian Federation Center of Open Systems Skoltech Moscow Russian Federation

ISBN: (数字)9781728193748

ISBN: (纸本)9781728193755

Video surveillance systems are a major multipurpose video data source for modern emergency management solutions. As their complexity and image quality grows, the requirements for data exchange channels, storage and processing units are becoming much more ***, a wide range of neural networks becomes a universal instrument for image analysis. Such algorithms require deployment of powerful HPC-class server *** this article, we propose a new adaptive approach to decentralized environment for video data storage and event-driven video processing for modern emergency management *** proposed solutions have been tested on different arrays of video data collected from various sources. These sources include city video surveillance systems, supermarket video surveillance systems, *** each of the listed examples, a discrete dynamic model has been developed based on video processing and event *** research resulted in a new data collection and analysis approach based on distributed video processing, reconstruction of 3D scenes and tactical situations detection.

关键词： video stream neural network artificial intelligence smart camera skeleton body model Smart cameras neural network Artificial Intelligence video monitoring video data Video stream SURVEILLANCE SYSTEMS data exchange crisis management

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 << < 135 136 137 138 139 140 141 142 143 144 > >>

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：