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

7,415 篇 会议
343 篇 期刊文献
57 册 图书
13 篇 学位论文

馆藏范围

7,828 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,446 篇 工学
- 3,415 篇 计算机科学与技术...
- 1,715 篇 软件工程
- 1,078 篇 电气工程
- 715 篇 信息与通信工程
- 343 篇 控制科学与工程
- 338 篇 电子科学与技术（可...
- 308 篇 光学工程
- 233 篇 机械工程
- 222 篇 生物医学工程（可授...
- 177 篇 仪器科学与技术
- 151 篇 生物工程
- 90 篇 测绘科学与技术
- 59 篇 化学工程与技术
- 56 篇 航空宇航科学与技...
- 48 篇 材料科学与工程（可...
- 47 篇 土木工程
- 41 篇 动力工程及工程热...
- 40 篇 力学（可授工学、理...
1,591 篇 理学
- 781 篇 物理学
- 690 篇 数学
- 175 篇 生物学
- 142 篇 系统科学
- 142 篇 统计学（可授理学、...
- 78 篇 化学
549 篇 医学
- 454 篇 临床医学
- 103 篇 特种医学
- 76 篇 基础医学(可授医学...
445 篇 管理学
- 287 篇 管理科学与工程(可...
- 176 篇 图书情报与档案管...
- 74 篇 工商管理
37 篇 法学
35 篇 农学
23 篇 经济学
20 篇 文学
17 篇 教育学
7 篇 艺术学
6 篇 军事学

主题

872 篇 parallel process...
691 篇 image processing
327 篇 image segmentati...
299 篇 concurrent compu...
273 篇 distributed comp...
266 篇 computational mo...
256 篇 feature extracti...
253 篇 computer archite...
216 篇 image reconstruc...
201 篇 image edge detec...
184 篇 image coding
177 篇 graphics process...
170 篇 iterative method...
165 篇 hardware
164 篇 neural networks
164 篇 algorithm design...
162 篇 deep learning
158 篇 computer science
142 篇 pixel
141 篇 graphics process...

机构

47 篇 national laborat...
25 篇 college of compu...
20 篇 natl univ def te...
19 篇 natl univ def te...
19 篇 science and tech...
14 篇 natl univ def te...
13 篇 school of comput...
12 篇 univ chinese aca...
11 篇 king saud univer...
11 篇 university of ch...
11 篇 natl univ def te...
10 篇 institute of inf...
10 篇 national univers...
9 篇 natl univ def te...
9 篇 national laborat...
8 篇 natl univ def te...
8 篇 department of co...
8 篇 national laborat...
8 篇 college of compu...
8 篇 school of cyber ...

作者

37 篇 dou yong
28 篇 luo zhigang
27 篇 yong dou
21 篇 zhang xiang
19 篇 zhigang luo
18 篇 li dongsheng
17 篇 naiyang guan
17 篇 qiao peng
15 篇 huang xuhui
15 篇 jie liu
14 篇 niu xin
13 篇 yijie wang
13 篇 lan long
13 篇 wang huaimin
12 篇 anon
11 篇 xiang zhang
11 篇 yang yang
11 篇 liu jie
11 篇 pesquet jean-chr...
11 篇 eyas el-qawasmeh

语言

7,541 篇 英文
231 篇 其他
54 篇 中文
7 篇 土耳其文
3 篇 俄文

检索条件"任意字段=Conference on Parallel and Distributed Methods for Image Processing"

共 7828 条记录，以下是2011-2020 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 the Acceleration of Deep Learning Model parallelism With Staleness

On the Acceleration of Deep Learning Model Parallelism With ...

引用

conference on Computer Vision and Pattern Recognition (CVPR)

作者： An Xu Zhouyuan Huo Heng Huang Electrical and Computer Engineering Department University of Pittsburgh PA USA JD Finance America Corporation Mountain View CA USA

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The inefficiency is caused by the backpropagation algorithm's forward locking, backward locking, and update locking problems. Existing solutions for acceleration either can only handle one locking problem or lead to severe accuracy loss or memory inefficiency. Moreover, none of them consider the straggler problem among devices. In this paper, we propose Layer-wise Staleness and a novel efficient training algorithm, Diversely Stale Parameters (DSP), to address these challenges. We also analyze the convergence of DSP with two popular gradient-based methods and prove that both of them are guaranteed to converge to critical points for non-convex problems. Finally, extensive experimental results on training deep learning models demonstrate that our proposed DSP algorithm can achieve significant training speedup with stronger robustness than compared methods.

关键词： Training parallel processing Computational modeling Neural networks Stochastic processes Acceleration Convergence

来源：评论

学校读者我要写书评

暂无评论

CUDA-Based parallel Computation Model for State Estimation

CUDA-Based Parallel Computation Model for State Estimation

引用

Chinese Control conference (CCC)

作者： Yueqi Liu Xiangyu Kong Yao Jin Key Laboratory of Smart Grid of Ministry of Education Tianjin University Tianjin China State Grid Tianjin Chengnan Electric Power Supply Company Tianjin China

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

With the development of the active distribution network (ADN), distributed state estimation (DSE) has become an inevitable trend for state estimation (SE). The efficient partitioned strategy is an essential prerequisite for DSE. However, the existing methods only consider the basic requirements of equilibrium connectivity, and the similarity of buses in one sub-region is ignored. A new partitioned strategy is proposed in this paper, this method learns from the idea of hierarchical clustering, the buses of the distribution network are aggregated to form sub-regions, and CUDA platform is used to realize the parallel computation of SE. The improved IEEE33-node system and a real distribution network are analyzed as a case study. The results show that, compared with traditional CSE, the estimation accuracy of DSE is higher than that of CSE, which indicates that the estimation accuracy of the proposed method is higher than that of CSE. Besides, compared with serial computation, this method can effectively reduce the running time of DSE in each sub-region and improve the overall calculation efficiency.

关键词： Graphics processing units Instruction sets Clustering algorithms Partitioning algorithms Voltage measurement Power measurement State estimation

来源：评论

学校读者我要写书评

暂无评论

Appraisal of Pre-processing Techniques for Automated Detection of Diabetic Retinopathy 5

Appraisal of Pre-processing Techniques for Automated Detecti...

引用

5th IEEE International conference on parallel, distributed and Grid Computing (PDGC)

作者： Bhardwaj, Charu Jain, Shruti Sood, Meenakshi Jaypee Univ Informat Technol Dept ECE Solan HP India

ISBN: (纸本)9781728106465

Retinopathy is a retinal vascular disease caused by abnormal blood flow that damages the retina and it accounts for 5% of blindness worldwide. There are different causes of Retinopathy as retinopathy of prematurity, diabetic retinopathy and hypertensive retinopathy;this paper mainly focuses on preprocessing techniques employed for the detection of diabetic retinopathy. In this work, literatures reporting different methods for automated diabetic retinopathy detection in color images of retina are analyzed for their strength and shortcoming. Extensive techniques for retinal image screening have been published so far thus this paper presents the evaluation of these methods on a common database of image screening. Different image pre-processing techniques are implemented on fundus images and their performance is compared using performance metrics like mean square error, peak signal to noise ratio and root mean square error. Pre-processing steps used in this work can also be applied to other images of interest to identify and recognize the objects in an image.

关键词： Computer aided screening diabetic retinopathy hypertensive retinopathy retinopathy of prematurity

来源：评论

学校读者我要写书评

暂无评论

Deep Sketch-Based Modeling: Tips and Tricks

Deep Sketch-Based Modeling: Tips and Tricks

引用

International conference on 3D Imaging, Modeling, processing, Visualization and Transmission (3DIMPVT)

作者： Yue Zhong Yulia Gryaditskaya Honggang Zhang Yi-Zhe Song SketchX CVSSP University of Surrey Beijing University of Posts and Telecommunications Abstract iFlyTek-Surrey Joint Research Centre on Artificial Intelligence

ISBN: (数字)9781728181288

ISBN: (纸本)9781728181295

Deep image-based modeling received lots of attention in recent years, yet the parallel problem of sketch-based modeling has only been briefly studied, often as a potential application. In this work, for the first time, we identify the main differences between sketch and image inputs: (i) style variance, (ii) imprecise perspective, and (iii) sparsity. We discuss why each of these differences can pose a challenge, and even make a certain class of image-based methods inapplicable. We study alternative solutions to address each of the difference. By doing so, we drive out a few important insights: (i) sparsity commonly results in an incorrect prediction of foreground versus background, (ii) diversity of human styles, if not taken into account, can lead to very poor generalization properties, and finally (iii) unless a dedicated sketching interface is used, one can not expect sketches to match a perspective of a fixed viewpoint. Finally, we compare a set of representative deep single-image modeling solutions and show how their performance can be improved to tackle sketch input by taking into consideration the identified critical differences.

关键词： Shape Three-dimensional displays image reconstruction Solid modeling Rendering (computer graphics) Surface reconstruction Strain

来源：评论

学校读者我要写书评

暂无评论

A MULTICORE CONVEX OPTIMIZATION ALGORITHM WITH APPLICATIONS TO VIDEO RESTORATION 25

A MULTICORE CONVEX OPTIMIZATION ALGORITHM WITH APPLICATIONS ...

引用

25th IEEE International conference on image processing (ICIP)

作者： Abboud, Feriel Chouzenoux, Emilie Pesquet, Jean-Christophe Talbot, Hugues WITBE France Puteaux La Defense France Univ Paris Saclay Cent Supelec INRIA Saclay CVN Paris France Univ Paris Est Marne La Vallee ESIEE CNRS LIGMUMR 8049 Champs Sur Marne France

ISBN: (纸本)9781479970612

In this paper, we present a new distributed algorithm for minimizing a sum of non-necessarily differentiable convex functions composed with arbitrary linear operators. The overall cost function is assumed strongly convex. Each involved function is associated with a node of a hypergraph having the ability to communicate with neighboring nodes sharing the same hyperedge. Our algorithm relies on a primal-dual splitting strategy with established convergence guarantees. We show how it can be efficiently implemented to take full advantage of a multicore architecture. The good numerical performance of the proposed approach is illustrated in a problem of video sequence denoising, where a significant speedup is achieved.

关键词： convex optimization distributed algorithms proximal methods video processing parallel programming

来源：评论

学校读者我要写书评

暂无评论

A Mobile Application for Sound Event Detection 28

A Mobile Application for Sound Event Detection

引用

28th International Joint conference on Artificial Intelligence

作者： Fu, Yingwei Xu, Kele Mi, Haibo Wang, Huaimin Wang, Dezhi Zhu, Boqing Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China Natl Univ Def Technol Coll Comp Changsha Peoples R China Natl Univ Def Technol Coll Meteorol & Oceanog Changsha Peoples R China

ISBN: (纸本)9780999241141

Sound event detection is intended to analyze and recognize the sound events in audio streams and it has widespread applications in real life. Recently, deep neural networks such as convolutional recurrent neural networks have shown state-of-the-art performance in this task. However, the previous methods were designed and implemented on devices with rich computing resources, and there are few applications on mobile devices. This paper focuses on the solution on the mobile platform for sound event detection. The architecture of the solution includes offline training and online detection. During offline training process, multi model-based distillation method is used to compress model to enable real-time detection. The online detection process includes acquisition of sensor data, processing of audio signals, and detecting and recording of sound events. Finally, we implement an application on the mobile device that can detect sound events in near real time.

关键词：

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

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

引用

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

作者： Analyn Yumang Glenn Magwili Sev Kyle C. Montoya Corleone Jorel G. Zaldarriaga School of EECE Mapúa University Intramuros Manila Philippines

ISBN: (纸本)9781665429979

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： Training Heating systems image edge detection Neural networks Inspection Convolutional neural networks Kernel

来源：评论

学校读者我要写书评

暂无评论

Forest Mapping from Hyperspectral image using Deep Belief Network 15

Forest Mapping from Hyperspectral Image using Deep Belief Ne...

引用

15th International conference on Mobile Ad-Hoc and Sensor Networks (MSN)

作者： Luo, Xianxian Xu, Songya Quanzhou Normal Univ Fac Math & Comp Sci Fujian Prov Key Lab Data Intens Comp Quanzhou Peoples R China Quanzhou Normal Univ Fac Educ Sci Quanzhou Peoples R China

ISBN: (纸本)9781728152127

Forest type is very important in the management of the forest ecosystem. Previous literatures demonstrate that deep belief network (DBN) gain the excellent classification performance. This research attempts to classify the forest type from hyperspectral image using DBN. To begin with, the Restricted Boltzmann Machines and deep belief networks are briefly reviewed. Then, the effect of network depth and the number of hidden units on the accuracy and Kappa efficient is discussed. Furthermore, forest type is classified using DBN by Python language, comparing with typical classification methods, such as support vector machine (SVM). The experimental results show that the number of layers is 3 and the number of nodes is 256 are the optimal network structure for forest type identification. The overall accuracy is 85.8% and the coefficient is 0.785, which is better than the classification performance of support vector machine. In general, deep belief network has the potential to be the dominant method of forest mapping by hyperspectral image.

关键词： Hyperspectral image deep belief network forest type TensorFlow spectral feature

来源：评论

学校读者我要写书评

暂无评论

Design and simulation of image nonlinear processing relational preprocessor based on iterational sorting node

Design and simulation of image nonlinear processing relation...

引用

conference on Optical Sensors

作者： Krasilenko, Vladimir G. Lazarev, Alexander A. Nikitovich, Diana, V Vinnitsa Social Econ Inst 86-131 Kelestskaya Str UA-21021 Vinnitsa Ukraine Vinnitsa Natl Tech Univ Vinnitsa Ukraine

ISBN: (数字)9781510627239

ISBN: (纸本)9781510627239

In this paper, we propose a new iterative process of sorting an array of signals, which differs from the known structures of sorting signals by uniformity, versatility, which allows direct and inverse sorting of an array of analog or digital signals. The basic elements of the proposed sorting structures are simple relational nodes for analogue signals from sensor devices and cameras. Such elements can be implemented on a different element basis, including, on devices for selecting a maximum or minimum of two analog or digital signals, which are implemented, in one of the variants, on CMOS current mirrors and carry out the function of continuous logic limited difference. We offer optoelectronic implementation of such basic relational element and a homogeneous sorting structure on such elements, consisting of two layers and a multichannel sampling and holding device. Nine signals corresponding to a selection window of a matrix sensor are fed to this structure, we sort them in five iterative steps, and at the output we receive the signals sorted by the rank, which, using the code controlled programmable multiplexer, generates an output signal, corresponding to the selected rank. We evaluate the technical parameters of such a relational preprocessor for nonlinear signal processing in image processors, sorting networks, multichannel parallel type sensor, processing, and encoding systems. The base cells consist of no more than 20 CMOS 1.5 mu m transistors, the total power consumption of the sorting node on 10 continuously logical base cells (CL BC) is 2mW, the supply voltage is 1.8 divided by 3.3V, the range of an input photocurrent is 0.1 divided by 24 mu A, the conversion cycle is 10 mu s, but can be improved by selecting other transistors and some modifications of the circuits. Such mixed analog processor is modeled in PSpice OrCad. The paper considers results of design and modeling of CL BC based on photosensitive cells with an extended electronic circuit and current

关键词： analog relational preprocessor image nonlinear processing simulation continuous logic current mirror sorting networks methods of selection and rank preprocessing rank filtering

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based Policies for Elastic Stream processing on Heterogeneous Resources 19

Reinforcement Learning Based Policies for Elastic Stream Pro...

引用

13th ACM International conference on distributed and Event-Based Systems (DEBS)

作者： Russo, Gabriele Russo Cardellini, Valeria Lo Presti, Francesco Univ Roma Tor Vergata Rome Italy

ISBN: (纸本)9781450367943

Data Stream processing (DSP) has emerged as a key enabler to develop pervasive services that require to process data in a near real-time fashion. DSP applications keep up with the high volume of produced data by scaling their execution on multiple computing nodes, so as to process the incoming data flow in parallel. Workloads variability requires to elastically adapt the application parallelism at run-time in order to avoid over-provisioning. Elasticity policies for DSP have been widely investigated, but mostly under the simplifying assumption of homogeneous infrastructures. The resulting solutions do not capture the richness and inherent complexity of modern infrastructures, where heterogeneous computing resources are available on-demand. In this paper, we formulate the problem of controlling elasticity on heterogeneous resources as a Markov Decision Process (MDP). The resulting MDP is not easily solved by traditional techniques due to state space explosion, and thus we show how linear Function Approximation and Tile Coding can be used to efficiently compute elasticity policies at run-time. In order to deal with parameters uncertainty, we integrate the proposed approach with Reinforcement Learning algorithms. Our numerical evaluation shows the efficacy of the presented solutions compared to standard methods in terms of accuracy and convergence speed.

关键词： Elasticity Reinforcement Learning Markov Decision Process Function Approximation Tile Coding

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500页 << < 198 199 200 201 202 203 204 205 206 207 > >>

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：