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

291 篇 会议
9 篇 期刊文献
3 册 图书

馆藏范围

303 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

224 篇 工学
- 216 篇 计算机科学与技术...
- 149 篇 软件工程
- 58 篇 信息与通信工程
- 12 篇 电气工程
- 6 篇 生物工程
- 4 篇 机械工程
- 3 篇 化学工程与技术
- 3 篇 生物医学工程（可授...
- 2 篇 电子科学与技术（可...
- 1 篇 仪器科学与技术
- 1 篇 控制科学与工程
- 1 篇 安全科学与工程
27 篇 理学
- 18 篇 数学
- 8 篇 生物学
- 3 篇 化学
- 3 篇 统计学（可授理学、...
- 2 篇 物理学
- 1 篇 系统科学
15 篇 管理学
- 13 篇 管理科学与工程(可...
- 5 篇 工商管理
- 3 篇 图书情报与档案管...
2 篇 法学
- 2 篇 社会学

主题

33 篇 cloud computing
16 篇 parallel computi...
11 篇 parallel process...
11 篇 distributed comp...
11 篇 distributed comp...
9 篇 computer archite...
9 篇 computational mo...
8 篇 parallel program...
8 篇 resource managem...
8 篇 distributed syst...
7 篇 peer to peer com...
7 篇 optimization
7 篇 high performance...
6 篇 fault tolerance
6 篇 educational inst...
6 篇 servers
6 篇 real-time system...
6 篇 protocols
6 篇 performance eval...
6 篇 gpu

机构

3 篇 a*star institute...
3 篇 topic committee ...
2 篇 univ adelaide sc...
2 篇 univ texas dept ...
2 篇 washington univ ...
2 篇 school of comput...
2 篇 laria laboratoir...
2 篇 guizhou universi...
2 篇 guizhou universi...
2 篇 beihang univ sta...
2 篇 graduate school ...
2 篇 los alamos natl ...
2 篇 tsinghua univers...
2 篇 univ calif san d...
2 篇 department of co...
2 篇 scripps res inst...
2 篇 kth royal inst t...
2 篇 natl univ def te...
2 篇 college of compu...
2 篇 kent state univ ...

作者

5 篇 li xiaorong
3 篇 xiaorong li
2 篇 seme david
2 篇 kanagasabai raja...
2 篇 cong guojing
2 篇 riccardo loti
2 篇 le duy ngan
2 篇 putchong uthayop...
2 篇 dongarra jack
2 篇 motomura shinich...
2 篇 taufer m
2 篇 ta nguyen binh d...
2 篇 kawamura takao
2 篇 vlassov vladimir
2 篇 kerbyson dj
2 篇 bader david a.
2 篇 tziritas nikos
2 篇 wu weigang
2 篇 liu jie
2 篇 coddington pd

语言

303 篇 英文

检索条件"任意字段=18th International Conference on Parallel and Distributed Computing Systems, PDCS 2005"

共 303 条记录，以下是21-30 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：

parallelNAS: A parallel and distributed System for Neural Architecture Search

ParallelNAS: A Parallel and Distributed System for Neural Ar...

引用

IEEE international conference on High Performance computing and Communications (HPCC)

作者： Xiaoyang Qu Jianzong Wang Jing Xiao Ping An Technology (Shenzhen) Co. Ltd. Shenzhen China

ISBN: (纸本)9781728176499;9781728176505

Although deep learning takes researchers out of complicated feature engineering, designing practical deep learning models is still a complicated process. Neural Architecture Search (NAS) is famous for automating the design of deep learning models. While the fundamental problem of NAS methods is time-consuming, parallel computing is an encouraging way to relieve this problem. We designed a two-level hierarchical parallel system called parallelNAS, comprising a parallel explorer and parallel evaluators. For the parallel explorer, a general-purposed distributed search framework is built on virtualized, massively-parallel, asynchronous infrastructure. For parallel evaluators, we integrate a segment-balanced sparsity scheme into a mainstream data-parallel architecture. the overall experiment results demonstrate that our distributed and parallel system can reach near-linear speedups on a cluster of 64 GPUs.

关键词： Deep learning Training Computational modeling High performance computing conferences Neural networks Computer architecture

来源：评论

学校读者我要写书评

暂无评论

DSANA: A distributed machine learning acceleration solution based on dynamic scheduling and network acceleration

DSANA: A distributed machine learning acceleration solution ...

引用

IEEE international conference on High Performance computing and Communications (HPCC)

作者： Runhua Zhang Guowei Shen Liangyi Gong Chun Guo Guizhou University China Guiyang Beihang University China Beijing Guizhou University China Guiyang Tsinghua University China Beijing

ISBN: (纸本)9781728176505

distributed machine learning(DML) has become a feasible solution to deal with the growing training data and models. Reviewing the existing architecture of DML, Parametric server(PS) architecture stands out in iterative convergence algorithms and widely deployed in practice, thanks to flexible expansion and so on. Under this architecture, the parameter synchronization mode based on Bulk Synchronous parallel(BSP) has become one of the research hotspots. As for the BSP mode, each iteration efficiency is determined by the slowest node in the cluster, therefore, the straggler problem becomes the main reason for reducing the efficiency of DML training, which is even more prominent in the heterogeneous cloud services. Existing works mainly focus on the straggler problem, and the importance of communication is usually ignored. However, inefficient communication is also one of the reasons for the inefficiency of DML iterations. In this paper, we propose DSANA, which first alleviates certain straggler problems by dynamically scheduling computation tasks. Secondly, DSANA improves the overlap of computation/communication by dividing larger transmission parameters, thus further improving the iteration efficiency of DML training. We conduct comparison experiments with the classic iterative algorithm PageRank on four different-scale data sets in two cloud service scenarios. the experimental results show that DSANA can improve the training efficiency to 36.6%$\sim$ 56.4% compared with the baseline solution.

关键词： Training Machine learning algorithms Processor scheduling Training data Computer architecture Machine learning Dynamic scheduling

来源：评论

学校读者我要写书评

暂无评论

parallel Task Graphs Scheduling Based on the Internal Structure 18th

Parallel Task Graphs Scheduling Based on the Internal Struct...

引用

18th Mexican international conference on Artificial Intelligence (MICAI)

作者： Velarde Martinez, Apolinar Inst Tecnol El Llano Aguascalientes Carretera Aguascalientes San Luis Potosi Km 18 Aguascalientes Aguascalientes Mexico

ISBN: (纸本)9783030337490;9783030337483

It is well known that parallel Task Graphs (PTG) are modeled with Directed Acyclic Graphs (DAG Tasks). DAG tasks are scheduled in Heterogeneous distributed computing systems (HDCS) for execution with different techniques which seek to reduce completion of each PTG. Proposed planning techniques generally only make use of the critical path in planning as an internal characteristic of the DAG Task, helping to optimize scheduling. In this study it is shown that analyzing other internal characteristics, such as layering and graph density aside from the critical path of DAG workflow tasks, before being scheduled in execution locations, can improve computer system performance, as well as optimize the use of their resources. For the above, the internal characteristics considered in this study of each DAG task are: the critical path, layering as well as graph density. the analyzed DAG tasks are synthetic loads produced with a graph generation algorithm as well as real application graphs. the findings obtained with the experiments performed show that the distribution estimation algorithm obtains better response times than the genetic algorithm.

关键词： Directed Acyclic Graph parallel Task Graphs Heterogeneous distributed computing systems

来源：评论

学校读者我要写书评

暂无评论

Interactive data science at scale 21

Interactive data science at scale

引用

Proceedings of the 18th ACM international conference on computing Frontiers

作者： David A. Bader New Jersey Institute of Technology

ISBN: (纸本)9781450384049

A real-world challenge in data science is to develop interactive methods for quickly analyzing new and novel data sets that are potentially of massive scale. In this talk, we discuss our development of suffix array and graph algorithms in the context of Arkouda, a NumPy-like replacement for interactive data science on tens of terabytes of data. Many real-world applications in bioinformatics, web information search and analysis, and lossless compression can be abstracted as string analysis. Suffix arrays are a very efficient data structure to support quick search of any string patterns. We have integrated the suffix array data structure (including its enhanced Longest Common Prefix (LCP) array) and the corresponding construction algorithm into Arkouda, thus providing Python users with a powerful method to support different types of string analysis. Our novel approach integrates a suffix array algorithm library into Arkouda so that the Arkouda runtime can select the large suffix array construction algorithm dynamically based on the dataset properties. Two of the implemented methods on the back-end of Arkouda include our novel O(n) time complexity skew algorithm in Chapel, and the DivSufSoft suffix array construction algorithm in C, which has higher time complexity but often is faster in practice. Experimental results show that, supported by Arkouda, Python users can build a large scale string's suffix array and LCP array in a Jupyter notebook easily without losing any performance compared with the directly back-end operation. Our future work is extending our self-developed algorithm to support multi-locale parallel execution, so that our algorithm can handle large strings on distributed systems. Graphs are widely used to abstract problems in domains such as social sciences, biological systems, and information systems. To support real-world large graph analysis in Arkouda, we first developed the array-based graph data structure which can be used like an adjacency matri

关键词： high performance data analytics data science high-performance computing graph algorithms

来源：评论

学校读者我要写书评

暂无评论

RDFM: Resilient distributed Factorization Machines 18th

RDFM: Resilient Distributed Factorization Machines

引用

18th international conference on Artificial Intelligence and Soft computing (ICAISC)

作者： da Silva, Andre Rodrigo Rodrigues, Leonardo M. Rech, Luciana de Oliveira Luiz, Aldelir Fernando Fed Univ Santa Catarina UFSC Dept Informat & Stat INE BR-88040900 Florianopolis SC Brazil

ISBN: (纸本)9783030209155;9783030209148

Factorization Machines algorithms have been successfully applied to recommender systems due to their ability to handle data sparsity and the cold-start problem. their scalability makes it suitable to produce evergrowing complex predictive models, which are based on Big Data without performance degradation. the algorithm has been scaled to contexts of distributed and parallel computation, but in general with the strong assumption that those environments are safe and are not subject to arbitrary errors, malicious attacks, and hardware failures. In this work, we show that a distributed average consensus strategy is capable to deal with unsafe and dynamic learning environments.

关键词： distributed average consensus Factorization Machines Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Real Time Key Frame Extraction through parallel Computation of Entropy Difference 18th

Real Time Key Frame Extraction Through Parallel Computation ...

引用

18th international conference on Computer Information systems and Industrial Management

作者： Gautam, Nandita Das, Debdoot Khatua, Sunirmal Saha, Banani Univ Calcutta Comp Sci Dept Kolkata 700098 India

ISBN: (纸本)9783030289560;9783030289577

the advancement of image processing in the field of Artificial Intelligence has created various research prospects in the area of object detection, pattern recognition etc. Capturing real time video stream for multiple cameras within a region of interest has become a common phenomenon for an Intelligent Situation Awareness System. Video processing is an important application which is rapidly developing nowadays as an area of extensive research. Content retrieval as well as information collection from a video requires both syntactic and semantic analysis. For a large video data, some set of frames are used to represent the video content. these are identified as key frames. Several algorithms have been defined to extract key frames from a stored video file. the existing algorithms that have been defined for key frame extraction are based on sequential mode. this paper looks into the extraction of key frames for any real time video stream. the experimental results show that there is an effective reduction in the execution time to a huge extent in the case of distributed processing as compared to the sequential processing of frames. In this paper, we propose a distributed framework to regulate the speed of key frame generation for heterogeneous speed of incoming video.

关键词： Real time streaming Key frames parallel computing Entropy

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Multi-Task Learning 18

Privacy-Preserving Multi-Task Learning

引用

18th IEEE international conference on Data Mining Workshops (ICDMW)

作者： Liu, Kunpeng Uplavikar, Nitish Jiang, Wei Fu, Yanjie Missouri Univ Sci & Technol Rolla MO 65409 USA Univ Missouri Columbia MO 65211 USA

ISBN: (纸本)9781538691595

Multi-task learning (MTL), improving learning performance by transferring information between related tasks, has drawn more and more attention in the data mining field. To tackle tasks whose data are stored at different locations (or nodes), distributed MTL was proposed. It not only enhances the learning performance but also improves the computing efficiency since it transforms the original centralized computing framework into a distributed computing framework under which computations can be done in parallel. the major drawback of the distributed MTL is a potential violation of confidentiality when the data stored at each node contain sensitive information (e.g., medical records). Some distributed MTL algorithms were designed to protect the original by only transferring aggregate information (e.g., supports or gradients) from each node to a server who combines the received information to produce the desired models. However, since aggregate data may still leak sensitive information, the security guarantee of the existing solutions cannot be formally proved or verified. thus, the goal of this paper is to develop a provable privacy-preserving multi-task learning (PP-MTL) protocol that incorporates the state of the art cryptographic techniques to achieve the best security guarantee. We also conducted experiments to demonstrate the efficiency of our proposed method.

关键词： Servers Cryptography Task analysis Protocols distributed databases Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of distributed Deep Learning Tools on Supercomputers 18th

Comparative Study of Distributed Deep Learning Tools on Supe...

引用

18th international conference on Algorithms and Architectures for parallel Processing (ICA3PP)

作者： Du, Xin Kuang, Di Ye, Yan Li, Xinxin Chen, Mengqiang Du, Yunfei Wu, Weigang Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou Peoples R China Guangdong Prov Key Lab Big Data Anal & Proc Guangzhou Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou Peoples R China

ISBN: (纸本)9783030050511;9783030050504

With the growth of the scale of data set and neural networks, the training time is increasing rapidly. distributed parallel training has been proposed to accelerate deep neural network training, and most efforts are made on top of GPU clusters. this paper focuses on the performance of distributed parallel training in CPU clusters of supercomputer systems. Using resources at the supercomputer system of "Tianhe-2", we conduct extensive evaluation of the performance of popular deep learning tools, including Caffe, TensorFlow, and BigDL, and several deep neural network models are tested, including AutoEncoder, LeNet, AlexNet and ResNet. the experiment results show that Caffe performs the best in communication efficiency and scalability. BigDL is the fastest in computing speed benefiting from its optimization for CPU, but it suffers from long communication delay due to the dependency on MapReduce framework. the insights and conclusions from our evaluation provides significant reference for improving resource utility of supercomputer resources in distributed deep learning.

关键词： distributed deep learning Tianhe-2 Speedup Performance evaluation parallel processing

来源：评论

学校读者我要写书评

暂无评论

New Multi-objectives Scheduling Strategies in Docker SwarmKit 18th

New Multi-objectives Scheduling Strategies in Docker SwarmKi...

引用

18th international conference on Algorithms and Architectures for parallel Processing (ICA3PP)

作者： Menouer, Tarek Cerin, Christophe Leclercq, Etienne Univ Paris 13 Sorbonne Paris Cite LIPN CNRS UMR 7030 F-93430 Villetaneuse France

ISBN: (纸本)9783030050573;9783030050566

this paper presents new multi-objectives scheduling strategies implemented in Docker SwarmKit. Docker SwarmKit is a container toolkit for orchestrating distributed systems at any scale. Currently, Docker SwarmKit has one scheduling strategy called Spread. Spread is based only on one objective to select from a set of cloud nodes, one node to execute a container. However, the containers submitted by users to be scheduled in Docker SwarmKit are configured according to multi-objectives criteria, as the number of CPUs and the memory size. To better address the multi-objectives configuration problem of containers, we introduce the concept and the implementation of new multi-objectives scheduling strategies adapted for Cloud computing environments and implemented in Docker SwarmKit. the principle of our multi-objectives strategies consist to select a node which has a good compromise between multi-objectives criteria to execute a container. the proposed scheduling strategies are based on a combinaison of PROMEthEE and Kung multi-objectives decision algorithms in order to place containers. the implementation in Docker SwarmKit and experiments of our new strategies demonstrate the potential of our approach under different scenarios.

关键词： systems software Scheduling and resource management Container technology Cloud computing Application of parallel and distributed algorithms

来源：评论

学校读者我要写书评

暂无评论

TAMM: A New Topology-Aware Mapping Method for parallel Applications on the Tianhe-2A Supercomputer 18th

TAMM: A New Topology-Aware Mapping Method for Parallel Appli...

引用

18th international conference on Algorithms and Architectures for parallel Processing (ICA3PP)

作者： Chen, Xinhai Liu, Jie Li, Shengguo Xie, Peizhen Chi, Lihua Wang, Qinglin Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Peoples R China Hunan Inst Traff Engn Inst Adv Sci & Technol Hengyang 421001 Peoples R China

ISBN: (纸本)9783030050511;9783030050504

With the increasing size of high performance computing systems, the expensive communication overhead between processors has become a key factor leading to the performance bottleneck. However, default process-to-processor mapping strategies do not take into account the topology of the interconnection network, and thus the distance spanned by communication messages may be particularly far. In order to enhance the communication locality, we propose a new topology-aware mapping method called TAMM. By generating an accurate description of the communication pattern and network topology, TAMM employs a two-step optimization strategy to obtain an efficient mapping solution for various parallel applications. this strategy first extracts an appropriate subset of all idle computing resources on the underlying system and then constructs an optimized one-to-one mapping with a refined iterative algorithm. Experimental results demonstrate that TAMM can effectively improve the communication performance on the Tianhe-2A supercomputer.

关键词： High performance computing systems Topology-aware mapping Communication pattern Network topology

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31页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：