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

2,952 篇 会议
39 篇 期刊文献
7 册 图书

馆藏范围

2,998 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,753 篇 工学
- 1,402 篇 计算机科学与技术...
- 683 篇 软件工程
- 488 篇 电气工程
- 394 篇 信息与通信工程
- 200 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
- 48 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
515 篇 理学
- 225 篇 物理学
- 188 篇 数学
- 143 篇 生物学
- 57 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

2,943 篇 英文
47 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 2998 条记录，以下是641-650 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：

Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for distributed Optimization 35

Smoothness Matrices Beat Smoothness Constants: Better Commun...

引用

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

作者： Safaryan, Mher Hanzely, Filip Richtarik, Peter KAUST Thuwal Saudi Arabia TTIC Chicago IL USA

ISBN: (纸本)9781713845393

Large scale distributed optimization has become the default tool for the training of supervised machine learning models with a large number of parameters and training data. Recent advancements in the field provide several mechanisms for speeding up the training, including compressed communication, variance reduction and acceleration. However, none of these methods is capable of exploiting the inherently rich data-dependent smoothness structure of the local losses beyond standard smoothness constants. In this paper, we argue that when training supervised models, smoothness matrices-information-rich generalizations of the ubiquitous smoothness constants-can and should be exploited for further dramatic gains, both in theory and practice. In order to further alleviate the communication burden inherent in distributed optimization, we propose a novel communication sparsification strategy that can take full advantage of the smoothness matrices associated with local losses. To showcase the power of this tool, we describe how our sparsification technique can be adapted to three distributed optimization algorithms-DCGD [Khirirat et al., 2018], DIANA [Mishchenko et al., 2019] and ADIANA [Li et al., 2020]-yielding significant savings in terms of communication complexity. The new methods always outperform the baselines, often dramatically so.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Detection of Employee Fatigue Based on Image processing Using Deep Learning Model

Detection of Employee Fatigue Based on Image Processing Usin...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International conference on

作者： Michael Ethan I Gede Putra Kusuma Computer Science Department Binus Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331506490

ISBN: (纸本)9798331506506

Fatigue in workplace is a common thing shared by all employees. Continuous exposure of fatigue could lead to negative productivity for companies. Current research on fatigue detection mostly focused to detect fatigues from a single 2D image data, meanwhile research on fatigue detection using each frames from video data is needed for better detection for fatigue process. The main advantage of using each timesteps of frames from video data which makes the model is able to predict long term dependency of fatigue person. To solve this problem, a deep learning model is proposed that could detect employee fatigue based on image processing using video data. Three models are used to train data using Convolutional neural network (CNN), which are Time distributed CNN LSTM, 3D CNN, and 3D CNN LSTM. Out of those three models, the best model to detect fatigue person from video data is Time distributed CNN Model with F-1 Score value of 0.77 and Accuracy Score of 0.76 for testing data. The model that gives best inference time is also Time distributed CNN Model with the average value of 382 miliseconds to detect fatigues from 58 testing data with each of the data has duration of 3 seconds and 12 frames.

关键词： Deep learning Three-dimensional displays Image processing Computational modeling distributed databases Fatigue Data models Convolutional neural networks Long short term memory Testing

来源：评论

学校读者我要写书评

暂无评论

Image Diversity Restoration Algorithm Based on Unsupervised Sample Guidance

Image Diversity Restoration Algorithm Based on Unsupervised ...

引用

Image processing, Electronics and Computers (IPEC), Asia-Pacific conference on

作者： Fan Yang Qihang Mo Huaizhong Lin Lixia Chen College of Computer Science and Technology Zhejiang University Hangzhou China School of Humanities and Communication Zhejiang Gongshang University Hangzhou China

ISBN: (数字)9798350374407

ISBN: (纸本)9798350374414

The existing image restoration algorithms are unable to solve the problem of modeling conditional probability distributions with known jointly distributed sample data, and an unsupervised sample-guided image diversification restoration algorithm (DIIUSG) is proposed to address this problem. The algorithm realizes image restoration by superimposing the hidden coding of the image to be restored and the hidden coding of the sample image in the hidden space, and then feeding them into the decoder. As the sample images are transformed continuously, the diversified restoration of images can be realized. The DIIUSG network architecture proposed in this paper consists of encoder, decoder and discriminator network structures and multiple loss functions. The network can automatically learn the image contents from the samples, and for the same image to be restored, different bootstrap samples will generate different results, thus realizing diversified image restoration. The proposed algorithm is validated on four standard datasets, including CelebA-HQ, and compared qualitatively and quantitatively with existing deep neural network-based image restoration algorithms, and the experimental results show that the proposed method performs well in several metrics. The experimental results also show that the proposed method solves the modeling problem of solving conditional probability distributions with known joint distribution samples.

关键词： Measurement Computers Image coding distributed databases network architecture Probability distribution Data models Image restoration Decoding Standards

来源：评论

学校读者我要写书评

暂无评论

Adaptive Convolutional neural network Structure for network Traffic Classification 27

Adaptive Convolutional Neural Network Structure for Network ...

引用

27th IEEE International conference on Parallel and distributed Systems, ICPADS 2021

作者： Han, Zhuang Guan, Jianfeng Yao, Yanan Yao, Su School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing China Beijing National Research Center for Information Science and Technology Tsinghua University Department of Computer Science and Technology Beijing China

ISBN: (纸本)9781665408783

network traffic classification has been highly concerned by academia and industry for decades. In recent years, deep learning has attracted many scholars to use it in network traffic classification due to its excellent performance in the fields of computer vision and natural language processing. However, the performance of the neural network depends on its structure in the same dataset. When looking for the neural network to classify network traffic, it is necessary to constantly adjust the structure of the neural network to achieve better results, which is very time-consuming and experience-dependent. To solve the above problem, this paper proposes an Adaptive Convolutional neural network Structure for network Traffic Classification (ACNNS-NTC) algorithm. The proposed algorithm first pre-processes the network traffic data used for training and testing, and then uses particle swarm optimization algorithm to optimize the network structure of the convolutional neural network, to generate convolutional neural network structure for network traffic classification, and verify the classification results. Experimental results show that the accuracies of the ACNNS-NTC algorithm on public datasets (ISCX-IDS2012, USTC-TFC2016, CIC-IDS2017) are above 99%. At the same time, the generated convolutional neural network has a more succinct structure and fewer model parameters compared with the existing methods. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Proceedings - 2022 23rd ACIS International Summer Virtual conference on Software Engineering, Artificial Intelligence, networking and Parallel/distributed Computing, SNPD-Summer 2022

Proceedings - 2022 23rd ACIS International Summer Virtual Co...

引用

23rd ACIS International Summer Virtual conference on Software Engineering, Artificial Intelligence, networking and Parallel/distributed Computing, SNPD-Summer 2022

ISBN: (纸本)9798350396379

The proceedings contain 27 papers. The topics discussed include: Tetris: automatic UAF exploit generation by manipulating layout based on reactivated paths;artificial neural network for processing fingerprint image noise;facial expression intensity estimation considering change characteristic of facial feature values for each facial expression;developing a gamification method based on motivation subscales for lifelogging applications;preliminary study of reasoning existing projects' descriptions based on classname word elements;construction and evaluation of a speech emotion classifier using LSTM;concurrency control program generation in genetic programming considering depth of the program tree;reconfiguration cost for reconfigurable computing architectures;and parallel binary search tree construction inspired by thread-level speculation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fault Detection and Identification of Fault location in Hybrid Microgrid using Artificial neural network

Fault Detection and Identification of Fault location in Hybr...

引用

International conference on Signal processing and Integrated networks (SPIN)

作者： Nirma Peter Pankaj Gupta Nidhi Goel Dept. of Electronics and Communication Indira Gandhi Delhi Technical University for Women Delhi India

Hybrid microgrids are emerging technology that integrates the key characteristics of AC and DC microgrids without requiring significant changes to the distribution network. However, its protection faces a lot of challenges due to the integration of various types of distributed Generation (DG). Integration of DGs into the power system causes a change in the magnitude and directions of short circuit current. Hence the design of the overcurrent protection in a microgrid becomes more complex. This drawback of the conventional protection method is solved by using intelligent protection schemes. In this work, the artificial neural network (ANN) is used for fault detection, classification, and locating faults in hybrid microgrids which are operated in islanded mode. This paper used MATLAB software for generating the dataset of fault voltages and currents from the test model. The trained ANN models were tested for 11 types of faults and nofault scenarios. Mean Square Error (MSE), regression plots, and receiver operating characteristics (ROC) were used to evaluate the performance of the neural network models. The results are encouraging.

关键词： Adaptation models Fault detection Short-circuit currents Microgrids Artificial neural networks Fault location Signal processing

来源：评论

学校读者我要写书评

暂无评论

8th Latin American High Performance Computing conference, CARLA 2021

8th Latin American High Performance Computing Conference, CA...

引用

8th Latin American High Performance Computing conference, CARLA 2021

ISBN: (纸本)9783031042089

The proceedings contain 18 papers. The special focus in this conference is on Latin American High Performance Computing. The topics include: Accelerating Smart City Simulations;distributed Artificial Intelligent Model Training and Evaluation;large-Scale distributed Deep Learning: A Study of Mechanisms and Trade-Offs with PyTorch;wind Prediction Using Deep Learning and High Performance Computing;an Analysis of neural Architecture Search and Hyper Parameter Optimization Methods;Solving the Heat Transfer Equation by a Finite Difference Method Using Multi-dimensional Arrays in CUDA as in Standard C;High-Throughput of Measure-Preserving Integrators Derived from the Liouville Operator for Molecular Dynamics Simulations on GPUs;an Efficient Parallel Model for Coupled Open-Porous Medium Problem Applied to Grain Drying processing;Energy Consumption Studies of WRF Executions with the LIMITLESS Monitor;Improving Performance of Long Short-Term Memory networks for Sentiment Analysis Using Multicore and GPU Architectures;a Methodology for Evaluating the Energy Efficiency of Post-Moore Architectures;Understanding COVID-19 Epidemic in Costa Rica Through network-Based Modeling;an Efficient Vectorized Auction Algorithm for Many-Core and Multicore Architectures;Green Energy HPC Data Centers to Improve processing Cost Efficiency;DICE: Generic Data Abstraction for Enhancing the Convergence of HPC and Big Data;a Comparative Study of Consensus Algorithms for distributed Systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-Performance Spectral Tensor Layer for Deep neural network

High-Performance Spectral Tensor Layer for Deep Neural Netwo...

引用

Intelligent Data and Security (IDS), IEEE International conference on

作者： Jie Zhang Weiqing Tong Xiao-Yang Liu School of Computer Engineering and Science Shanghai University Department of Computer Science Rensselaer Polytechnic Institute

ISBN: (数字)9798350389487

ISBN: (纸本)9798350389494

Training on large-scale image datasets enables better performance of deep neural networks (DNNs). To have a rea-sonable training time, DNNs are usually trained on large-scale datasets using distributed training. However, the communication overhead of distributed training makes the training more costly and inefficient. And training on large-scale dataset with large batch size has a large G PU memory footprint. In this paper, we present the high-performance spectral tensor layer for distributed training. By tensorizing image data and transforming it to the spectral domain, we split the training dataset into multiple independent sub-datasets. Building multiple sub-networks and utilizing ensemble learning, we implement a distributed training method without communication overhead. Compared to training on a single GPU using CUDA cores, our method achieves a speedup of 5.0 x at four training nodes and a speedup of 18.2 x at sixteen training nodes for training on the ImageN et-IK dataset. We also have an experiment for training on the ImageNet-21K dataset and our method achieves a speedup of 16.4x at 16 training nodes.

关键词： Training Tensors Accuracy Memory management Data preprocessing Graphics processing units Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

GRAPH neural networkS FOR DECENTRALIZED CONTROLLERS

GRAPH NEURAL NETWORKS FOR DECENTRALIZED CONTROLLERS

引用

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

作者： Gama, Fernando Tolstaya, Ekaterina Ribeiro, Alejandro Univ Calif Berkeley Elect Engn & Comp Sci Dept Berkeley CA 94720 USA Univ Penn Dept Elect & Syst Engn Philadelphia PA 19104 USA

ISBN: (纸本)9781728176055

Dynamical systems comprised of autonomous agents arise in many relevant problems such as multi-agent robotics, smart grids, or smart cities. Controlling these systems is of paramount importance to guarantee a successful deployment. Optimal centralized controllers are readily available but face limitations in terms of scalability and practical implementation. Optimal decentralized controllers, on the other hand, are difficult to find. In this paper, we propose a framework using graph neural networks (GNNs) to learn decentralized controllers from data. While GNNs are naturally distributed architectures, making them perfectly suited for the task, we adapt them to handle delayed communications as well. Furthermore, they are equivariant and stable, leading to good scalability and transferability properties. The problem of flocking is explored to illustrate the potential of GNNs in learning decentralized controllers.

关键词： decentralized control graph neural networks graph recurrent neural networks graph signal processing network systems

来源：评论

学校读者我要写书评

暂无评论

distributed Machine Learning with Sparse Heterogeneous Data 35

Distributed Machine Learning with Sparse Heterogeneous Data

引用

35th conference on neural Information processing Systems (NeurIPS)

作者： Richards, Dominic Negahban, Sahand N. Rebeschini, Patrick Univ Oxford Dept Stat 24-29 St Giles Oxford OX1 3LB England Yale Univ Dept Stat & Data Sci 24 Hillhouse Ave New Haven CT 06510 USA

ISBN: (纸本)9781713845393

Motivated by distributed machine learning settings such as Federated Learning, we consider the problem of fitting a statistical model across a distributed collection of heterogeneous data sets whose similarity structure is encoded by a graph topology. Precisely, we analyse the case where each node is associated with fitting a sparse linear model, and edges join two nodes if the difference of their solutions is also sparse. We propose a method based on Basis Pursuit Denoising with a total variation penalty, and provide finite sample guarantees for sub-Gaussian design matrices. Taking the root of the tree as a reference node, we show that if the sparsity of the differences across nodes is smaller than the sparsity at the root, then recovery is successful with fewer samples than by solving the problems independently, or by using methods that rely on a large overlap in the signal supports, such as the group Lasso. We consider both the noiseless and noisy setting, and numerically investigate the performance of distributed methods based on distributed Alternating Direction Methods of Multipliers (ADMM) and hyperspectral unmixing.

关键词： Sampling

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300页 << < 61 62 63 64 65 66 67 68 69 70 > >>

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：