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1111-1120 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：

OVERLAP LOCAL-SGD: AN ALGORITHMIC APPROACH TO HIDE COMMUNICATION DELAYS IN distributed SGD

OVERLAP LOCAL-SGD: AN ALGORITHMIC APPROACH TO HIDE COMMUNICA...

引用

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

作者： Wang, Jianyu Liang, Hao Joshi, Gauri Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781509066315

distributed stochastic gradient descent (SGD) is essential for scaling the machine learning algorithms to a large number of computing nodes. However, the infrastructures variability such as high communication delay or random node slowdown greatly impedes the performance of distributed SGD algorithm, especially in a wireless system or sensor networks. In this paper, we propose an algorithmic approach named Overlap Local-SGD (and its momentum variant) to overlap communication and computation so as to speedup the distributed training procedure. The approach can help to mitigate the straggler effects as well. We achieve this by adding an anchor model on each node. After multiple local updates, locally trained models will be pulled back towards the synchronized anchor model rather than communicating with others. Experimental results of training a deep neural network on CIFAR-10 dataset demonstrate the effectiveness of Overlap Local-SGD. We also provide a convergence guarantee for the proposed algorithm under non-convex objective functions.

关键词： Local SGD communication efficient training federated learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Algorithm to Mitigate Protection Challenges in a Distribution System Integrated with Inverter-Based distributed Energy Resources

A Novel Algorithm to Mitigate Protection Challenges in a Dis...

引用

IEEE International Symposium on Intelligent Signal processing and Communication Systems (ISPACS)

作者： Arunodai Chanda Varun Chhibbar Carolina Arbona Prasad Dongale Burns & McDonnell Atlanta GA USA Burns & McDonnell Kansas City MO USA

To overcome the challenges on global warming due to fossil-fuels based generation, renewable distributed energy resources (DERs) like inverter based DERs (IBDERs) have been significantly integrated into distribution systems. However, during a short-circuit fault, the fault current contribution from IBDER is very low due to strong control of the inverters. The low fault current creates sensitivity issues in the overcurrent relay of IBDER which can create protection failure. To overcome this issue, a new way of implementing machine learning based algorithm named Radial Basis Function neural network (RBFNN) will be proposed. This method will use the time series data to detect fault current contribution from IBDER fast and accurately. In a distribution system, there could be a recloser on the feeder between a feeder breaker and IBDER. An ideal scenario is the feeder breaker and recloser to trip for any faults between them. In this case, the overcurrent relay of IBDER should not operate to avoid any unnecessary outages to the customers between the recloser and IBDER. However, if RBFNN algorithm is implemented in the overcurrent relay of IBDER then it will trip for all faults on the feeder along with feeder breaker due to its fast operation. To avoid such operation, this paper is proposing the RBFNN algorithm for both recloser relay and IBDER relay which will trip the recloser relay instead of the IBDER relay for any faults between the feeder breaker and recloser. However, the RBFNN algorithm of recloser relay will be blocked for any faults between the recloser and IBDER. Simulations have been performed on a distribution system with feeder breaker, recloser and IBDER for various fault scenarios to prove the benefits of this algorithm. This paper also shows the coordination of RBFNN algorithms between the recloser and IBDER for faults between feeder breaker and recloser to avoid any miscoordination.

关键词： Renewable energy sources Sensitivity Time series analysis Radial basis function networks Inverters distributed power generation Relays

来源：评论

学校读者我要写书评

暂无评论

VRFormer: 360-Degree Video Streaming with FoV Combined Prediction and Super resolution

VRFormer: 360-Degree Video Streaming with FoV Combined Predi...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Zhihao Zhang Haipeng Du Shouqin Huang Weizhan Zhang Qinghua Zheng Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University School of Continuing Education Xi'an Jiaotong University

360-degree video has shown great potential to the mainstream since its immersive experience. However, 360-degree video streaming requires ultrahigh bandwidth and low latency, which limit the improvement of user quality of experience (QoE). Currently, methods combining field of view (FoV) prediction and adaptive video streaming provide an effective method for addressing the above issues. However, existing FoV prediction methods based on recurrent neural networks (RNN) cannot capture long-range dependency from input to output. Current deep reinforcement learning (DRL)-based adaptive strategies fail to estimate the future bandwidth with high accuracy and fully explore the capability of VR devices. To ameliorate these limitations, we design a DRL-based 360-degree video streaming method named VRFormer with FoV combined prediction and super resolution (SR). First, we adopt a content-aware transformer-based encoder-decoder network to make the long-term FoV prediction. It combines the user's head movement history, eye-tracking history, and user attention extracted from a convolutional neural network (CNN)-based network. Second, we introduce a DNN-based SR network running on VR devices to reconstruct high-definition video content. Finally, we apply a DRL-based network to adaptively allocate rates for future tiles and dynamically control video content reconstruction. Experiments have verified that the proposed method can effectively improve the quality of experience (QoE) of the user's viewing experience compared to the state-of-the-art methods.

关键词： Recurrent neural networks Superresolution Bandwidth Reinforcement learning Prediction methods Streaming media Transformers

来源：评论

学校读者我要写书评

暂无评论

ReSLB: Load Balanced Workflow for distributed Deep Learning Mass Spectrometry Database

ReSLB: Load Balanced Workflow for Distributed Deep Learning ...

引用

IEEE International conference on High Performance Computing and Communications (HPCC)

作者： Li Mocheng Liu Yang Ou Yang Chen Zhiguang Xiao Nong Chen Tao Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China School of Computer Sun Yat-sen University Guangzhou China State Key Laboratory of Proteomics Beijing Proteome Research Center National Center for Protein Sciences(Beijing) Beijing Institute of Lifeomics Beijing China

The proteomics data analysis pipeline based on the shotgun method requires efficient data processing methods. The parallel algorithm of mass spectrometry database search faces the problems of rapidly expanding database size but low scalability. The heterogeneous database search algorithm based on deep learning is an effective way to solve this problem. Still, the deep learning-based distributed parallel database search algorithm is lacking. This paper analyzes the database searching computational load using a neural network and designs ReSLB, a workflow for the restricted search of mass spectrometry data based on GPU cluster and neural network scoring algorithm. This work aims to ensure the high scalability of future deep learning-based mass spectrometry distributed databases. In the performance estimation of 256 GPUs, the load imbalance of less than 30% and the parallel efficiency of 60% are achieved. Compared with state-of-the-art, the time cost is reduced by 75%, and the parallel efficiency from 1 to 256 GPUs is 3.6x higher than that.

关键词： Deep learning Scalability neural networks Data preprocessing distributed databases Graphics processing units Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

distributed optimization for overparameterized problems: achieving optimal dimension independent communication complexity 22

Distributed optimization for overparameterized problems: ach...

引用

Proceedings of the 36th International conference on neural Information processing Systems

作者： Bingqing Song Ioannis Tsaknakis Chung-Yiu Yau Hoi-To Wai Mingyi Hong Department of ECE University of Minnesota Department of SEEM Chinese University of Hong Kong

ISBN: (纸本)9781713871088

Decentralized optimization are playing an important role in applications such as training large machine learning models, among others. Despite its superior practical performance, there has been some lack of fundamental understanding about its theoretical properties. In this work, we address the following open research question: To train an overparameterized model over a set of distributed nodes, what is the minimum communication overhead (in terms of the bits got exchanged) that the system needs to sustain, while still achieving (near) zero training loss? We show that for a class of overparameterized models where the number of parameters D is much larger than the total data samples N, the best possible communication complexity is Ω(N), which is independent of the problem dimension D. Further, for a few specific overparameterized models (i.e., the linear regression, and certain multi-layer neural network with one wide layer), we develop a set of algorithms which uses certain linear compression followed by adaptive quantization, and show that they achieve dimension independent, near-optimal communication complexity. To our knowledge, this is the first time that dimension independent communication complexity has been shown for distributed optimization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Method for Finding Mislabeled Samples of Similar Chinese Characters

An Efficient Method for Finding Mislabeled Samples of Simila...

引用

IEEE International Symposium on Parallel and distributed processing with Applications and IEEE International conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Yue Chen Xiaoying Zhu Jihong Huang Guangyao Pang Baoxing Pu Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou China Guangxi Colleges and Universities Key Laboratory of Industry Software Technology Wuzhou University Wuzhou China

Convolutional neural networks for offline handwritten Chinese character recognition require a large number of samples to train the model, the mislabeled samples in the training set will reduce the recognition accuracy of the model, while similar Chinese character samples are the most prone to be mislabeled. In this paper, we propose a method to find the mislabeled samples of similar handwritten Chinese character pairs by differential features based recognition combined with manual verification, which can significantly reduce the time required to find the mislabeled samples. The method was applied to the similar character pair of E-B” whose handwritten samples are easy to be mislabeled. The experiments show that the proposed method can narrow down the scope of candidate mislabeled samples and improve the efficiency of manual verification, and find four times more mislabeled samples than convolutional neural network based method.

关键词： Training Handwriting recognition neural networks Manuals Ubiquitous computing Character recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Handwritten Chinese Character Recognition Based on Convolutional neural networks and TrueType Font Template Matching

Handwritten Chinese Character Recognition Based on Convoluti...

引用

IEEE International Symposium on Parallel and distributed processing with Applications and IEEE International conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Yue Chen Guangyao Pang Xiaoying Zhu Baoxing Pu Jihong Huang Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou China Guangxi Colleges and Universities Key Laboratory of Industry Software Technology Wuzhou University Wuzhou China

Convolutional neural networks(CNN) have made significant advances in offline handwritten Chinese character recognition, CNN recognize characters based on local feature but not making use of the overall topology of the character to improve recognition accuracy. In this paper, we propose a method for handwritten Chinese character recognition by using CNN combined with TrueType font template matching. Firstly, a trained CNN is used to recognize the handwritten Chinese character, the output Top-N are selected as the candidate characters, and then the handwritten Chinese character is linearly transformed and matched with the TrueType font templates of the candidate characters respectively, the best matching candidate character is selected as the result. The experiments show that the method can combine the speed of CNN and the accuracy of template matching effectively, has higher accuracy than conventional CNN, especially for specific types of handwritten Chinese characters recognition.

关键词： Handwriting recognition network topology neural networks Stroke (medical condition) Ubiquitous computing Topology Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

WGeod: A General and Efficient FPGA Accelerator for Object Detection

WGeod: A General and Efficient FPGA Accelerator for Object D...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Zihan Wang Mengying Zhao Lei Gong Chao Wang School of Computer Science and Technology University of Science and Technology of China University of Science and Technology of China Suzhou Institute for Advanced Research School of Computer Science and Technology Shandong University wangzh

With the development of high-performance embedded applications, object detection algorithms are starting to be deployed to embedded devices with fewer resources, and the classification and location information they provide is the basis for making further decisions in some high-performance embedded applications, so real-time and low-power consumption are especially needed. In this paper, we propose an FPGA-based neural network ac-celerator for object detection, which improves the speed, throughput and power efficiency of the inference with little loss of accuracy. The accelerator balances the speed difference between computation and memory access. The accelerator is scalable and can be configured for CNN of any size, and is general enough to support the acceleration of YOLOv2, YOLOv3 and their Tiny versions. We deploy the Tiny YOLOv3 network on FPGA-based accelerator, CPU and GPU platforms, and compare them in terms of speed, throughput and power efficiency. For the Tiny YOLOv3 network, the accelerator delivers an FPS of 1.61 and throughput of 8.95 GOP/s, which is 23.81x, 4.11x and 3.00x better than the Intel Core i5-10210U CPU with the 00, 01 and O3 compilation optimization options respectively. With 2.11 W of power, the accelerator delivers a power efficiency of 4.24 GOP/s/W, which is 141.33x, 28.27x and 21.20x better than the Intel Core i5-10210U CPU with the 00, O1 and O3 options respectively.

关键词： neural networks Graphics processing units Object detection Throughput Real-time systems Classification algorithms Optimization

来源：评论

学校读者我要写书评

暂无评论

Determination of Shelled Corn Damages using Colored Image Edge Detection with Convolutional neural network 12

Determination of Shelled Corn Damages using Colored Image Ed...

引用

IEEE 12th International conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM)

作者： Yumang, Analyn Magwili, Glenn Montoya, Sev Kyle C. Zaldarriaga, Corleone Jorel G. Mapua Univ Sch EECE Manila Philippines

ISBN: (纸本)9781665419710

In the Philippines corn is one of the top agricultural products produced in the country, specifically yellow corn. It is distributed in various cities and provinces to consumers. It is important that the corn kernels to undergo quality assurance before releasing them to the consumers. The methods for evaluating and qualifying corn kernels that are employed by most farms in the country are only done by manual human inspection and these methods are inconsistent which results to inaccurate findings. This is more prevalent when dealing with large amounts of kernels that need to be qualified. This study offers to reduce those inconsistencies by implementing a neural network-assisted method of inspection. The damages to corn kernels can be determined by its physical attributes and as such, the neural network will easily detect the type of damage within a given sample. Aside from the healthy kernels, the types of damage that was included in this study are the following: drier damage, heat damage, heat damage (drier phase), OCOL (Other Color) Type A and OCOL Type B .The neural network that will be used will be a Convolutional neural network wherein the images of the samples are subjected to layers of processing. This study also uses Colored Image Edge Detection. The detection method used in this study has obtained an accuracy rating of 96.66%.

关键词： Convolutional neural network Corn kernels Edge Detection Colored Image Edge Detection

来源：评论

学校读者我要写书评

暂无评论

Respipe: Resilient Model-distributed DNN Training at Edge networks

Respipe: Resilient Model-Distributed DNN Training at Edge Ne...

引用

IEEE International conference on Acoustics, Speech and Signal processing

作者： Pengzhen Li Erdem Koyuncu Hulya Seferoglu University of Illinois at Chicago

The traditional approach to distributed deep neural network (DNN) training is data-distributed learning, which partitions and distributes data to workers. This approach, although has good convergence properties, has high communication cost, which puts a strain especially on edge systems and increases delay. An emerging approach is model-distributed learning, where a training model is distributed across workers. Model-distributed learning is a promising approach to reduce communication and storage costs, which is crucial for edge systems. In this paper, we design ResPipe, a novel resilient model-distributed DNN training mechanism against delayed/failed workers. We analyze the communication cost of ResPipe and demonstrate the trade-off between resiliency and communication cost. We implement ResPipe in a real testbed consisting of Android-based smartphones, and show that it improves the convergence rate and accuracy of training for convolutional neural networks (CNNs).

关键词： Training neural networks distributed databases Signal processing Delays Speech processing Smart phones

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 << < 108 109 110 111 112 113 114 115 116 117 > >>

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：