检索结果-内蒙古大学图书馆

Advanced learning technologies for deep learning

NTT Technical Review 2018年第8期16卷 37-41页

作者： Ida, Yasutoshi Kanai, Sekitoshi Fujiwara, Yasuhiro Yagi, Satoshi Iida, Yasuhiro Distributed Computing Technology Project NTT Software Innovation Center Japan

NTT is focusing on artificial intelligence (AI) as a key technology in developing business strategies. The NTT laboratories have been engaged in research and development (R&D) of deep learning algorithms, which play a central role in AI. This article presents an overview of our R&D of novel algorithms that speed up and stabilize deep learning and touches on our collaboration with several partners to verify those algorithms. © 2018 Nippon Telegraph and Telephone Corp. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

R&D efforts in storage virtualization technologies

引用

NTT Technical Review 2015年第2期13卷

作者： Fukumoto, Yoshifumi Naito, Ichibee Hitaka, Toshio Shiraishi, Masahiro Distributed Computing Technology Project NTT Software Innovation Center Japan

The NTT Software Innovation Center is active in the research and development (R&D) of storage virtualization technologies. This article introduces its R&D of Sheepdog, a distributed block storage system that can be used from any file system, and OpenStack Swift, a robust distributed object storage system featuring high operability.

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

Advanced processing and analytics for large-scale graphs

引用

NTT Technical Review 2016年第2期14卷

作者： Iida, Yasuhiro Kishimoto, Yasunari Fujiwara, Yasuhiro Shiokawa, Hiroaki Arai, Junya Iwamura, Sotetsu Distributed Computing Technology Project NTT Software Innovation Center Japan

Expectations have been rising in recent years for capabilities to extract hidden knowledge in friendship relationships, product purchase relationships, and business transaction relationships for use in promoting sales, increasing work efficiency, and other such purposes. A graph is a data structure that represents data relationships. Data mining on graph data is called graph mining. Here, we describe advanced graph mining techniques that can be used to instantly discover hidden knowledge in large-scale graphs which lead to improved work efficiency through high-speed graph processing. We also present examples of graph mining applications.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

PostgreSQL: Leader in cost reduction

引用

NTT Technical Review 2014年第6期12卷

作者： Kawada, Akiyoshi Nishimurab, Go Teramoto, Junji Fujita, Etsuro Yamamuro, Takeshi Wakamori, Takuma Infrastructure Technology Unit NTT Open Source Software Center Japan Distributed Computing Technology Project NTT Software Innovation Center Japan

The NTT Open Source Software Center is conducting research and development on the PostgreSQL open-source database management system in order to develop and spread open source software (OSS). Recent advances in the development of PostgreSQL have brought it to a level of usability adequate for commercial systems, and due to its great cost-reducing effects relative to commercial products, it is receiving much attention and even being introduced for core systems. In this article, we introduce new functionality in the latest version, PostgreSQL 9.3, released in September 2013, and outline NTT's OSS development policies. We also introduce the SQL/MED (Structured Query Language/Management of External Data) indexing engine, which was developed by the authors as infrastructure for log analysis and an area for expanding applications of PostgreSQL.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

A Hadoop Performance Model for Multi-Rack Clusters

A Hadoop Performance Model for Multi-Rack Clusters

引用

International Conference on Computer Science and Information technology

作者： Jungkyu Han Masakuni Ishii Hiroyuki Makino Distributed Computing Technology Project Software Innovation Center Nippon Telegraph and Telephone Corporation Tokyo Japan

ISBN: (纸本)9781467356107

Hadoop becomes de facto standard framework for big data analysis due to its scalability. Despite of the importance of Hadoop's scalability, there are a few works have been made on the scalability in multi-rack clusters. In multi-rack clusters of real world, network topology becomes a major scalability bottleneck due to the limited network switch capacity. It is a waste of resources to add servers to a Hadoop cluster in such situation. Therefore, it is helpful for users to save cost by efficiently measuring the network influence to Hadoop before they add a new server to their clusters. In this paper, we describe a Hadoop performance model for the multi-rack clusters. We modeled network influence on Hadoop and achieved about 95% accuracy to the real measurement. Furthermore, we predicted Hadoop scalability in large clusters with our model and show Hadoop scales enough even in multi-rack clusters.

关键词： Hadoop Map-Reduce Performance Modeling distributed Data Processing Scalability distributed DATA PROCESSING PERFORMANCE MODELING Servers Clusters Network topology

来源：评论

学校读者我要写书评

暂无评论

Design and performance evaluation for Hadoop clusters on virtualized environment

Design and performance evaluation for Hadoop clusters on vir...

引用

International Conference on Information Networking

作者： Masakuni Ishii Jungkyu Han Hiroyuki Makino Distributed Computing Technology Project Software Innovation Center Nippon Telegraph and Telephone Corporation Tokyo Japan

Hadoop an implementation of Google's MapReduce, is widely used in these days for big data analysis. Yahoo Inc. operated 25 PB with 25,000 nodes in 2010. The resource management for such large number of nodes is quite difficult from the aspects of configuration, deployment and efficient resource utilization. By deploying virtual machines (VMs), Hadoop management becomes much easier. Amazon already released the Hadoop on Xen-virtualized environment as Elastic MapReduce. However, Hadoop on VM clusters degrades its performance due to the overhead of the virtualization. Thus, it is important to minimize the overhead. We build a Hadoop performance model and examine how the performance is affected by changing VM configuration, allocation of VMs over physical machines, and multiplicity of jobs. We find that performance of the I/O-intensive jobs is more sensitive to the virtualization overhead than that of CPU-intensive jobs. The performance degradation caused by the VM configuration change is 55% at most and the one caused by allocation change is 18% at most for I/O-intensive jobs. For I/O intensive jobs, the best practice is to increase the number of VMs and not to increase the number of VCPUs in a VM, to allocate VMs widely over physical servers, and to decrease the number of simultaneous executed jobs. The main factor of virtualization overhead is disk I/O shared by multiple VMs in a physical server.

关键词： Servers Resource management Degradation Throughput Virtualization Equations Switches

来源：评论

学校读者我要写书评

暂无评论

Efficient mining algorithms for large-scale graphs

引用

NTT Technical Review 2013年第12期11卷

作者： Kishimoto, Yasunari Shiokawa, Hiroaki Fujiwara, Yasuhiro Onizuka, Makoto Distributed Computing Technology Project NTT Software Tonovation Center United States NTT Software Innovation Center United States Disnnguishcd Technical NTT Software Innovation Center University of Elcctro-Commnnicatioos Japan

This article describes efficient graph mining algorithms designed for analyzing large-scale graph data such as social graphs. Graph mining is a technique to analyze the structure of graphs consisting of nodes and edges. We have developed efficient algorithms for two mining tasks: clustering and computing personalized PageRank, for large-scale graphs.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Auction-Based Job Scheduling for Smart Manufacturing 17

Auction-Based Job Scheduling for Smart Manufacturing

引用

17th IEEE International Symposium on Applied Computational Intelligence and Informatics, SACI 2023

作者： Gatial, Emil Balogh, Zoltan Dolatabadi, Sepideh Hassankhani Ghorbel, Hatem Carrino, Stefano Dreyer, Jonathan Montequin, Vicente Rodriguez Gligor, Adrian Iantovics, Laszlo Barna Institute of Informatics Sav Parallel and Distributed Computing Bratislava Slovakia Institute of Informatics Sav Modelling and Control of Discrete Processes Bratislava Slovakia Haute École Arc Ingénierie HES-SO St-Imier Switzerland University of Oviedo Project Engineering Area Oviedo Spain University of Medicine Pharmacy Science and Technology of Targu Mures Electrical Engineering and Information Technology 'George Emil Palade' Targu Mures Romania

ISBN: (纸本)9798350321104

The paper describes a real-time job scheduling method designed for production of goods with different characteristics on machines with different processing parameters. The objective is to maximize the global reward of the factory as a sum of the rewards for each machine job. Traditionally, the task assignment problems deal with the assignment of m-tasks to n-agents and are calculated by analytical methods or heuristics. The proposed method is based on online auctions that distributes the tasks to the machines using the software agents. The method is implemented using the ERTS (Erlang Real-Time System) that allows adopting the features of fault-tolerance and real-time processing. The paper starts with introduction and review of related state-of-the-art. The following chapter briefly describes the problem and the specific requirements. The following chapter describes the software architecture of the online auction system, the use-case and the motivation for developing this method. The proposed method auction-based task assignment and its implementation are described in the next chapters. At the end of the work, the results of the method are presented in comparison with the optimal solution and the performance characteristics are also described. In the conclusion, possible advances and future work are proposed. © 2023 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Auction-Based Job Scheduling for Smart Manufacturing

Auction-Based Job Scheduling for Smart Manufacturing

引用

International Symposium on Applied Computational Intelligence and Informatics ( SACI)

作者： Emil Gatial Zoltán Balogh Sepideh Hassankhani Dolatabadi Hatem Ghorbel Stefano Carrino Jonathan Dreyer Vicente Rodríguez Montequín Adrian Gligor Laszlo Barna Iantovics Parallel and distributed computing Institute of Informatics SAV Bratislava Slovakia Modelling and Control of Discrete Processes Institute of Informatics SAV Bratislava Slovakia Haute École Arc Ingénierie HES-SO St-Imier Switzerland Project Engineering Area University of Oviedo Oviedo Spain Electrical Engineering and Information Technology “George Emil Palade” University of Medicine Pharmacy Science and Technology of Targu Mures Targu Mures Romania

关键词：

来源：评论

学校读者我要写书评

暂无评论

Audit Workpaper Automation at Boston College

引用

EDPACS 2006年第7期27卷 1-8页

作者： Pamela Jerskey The IS audit manager at Boston College. She is responsible for conducting audits in information technology and distributed departmental applications. These assignments focus on controls over program security computer operations data file security system software network configurations and end-user computing. During 1999 Jerskey was the program manager of the Y2K project at Boston College. The Boston College Internal Audit World Wide Web home page can be accessed at: http://www.bc.edu/bc_org/fvp/ia/home/home.html

The Boston College Internal Audit Department has developed best practices that will enable its auditors to face the techno-logical challenges and changes of the next millennium. In ad-dition to automating the department's workpapers, the information-processing applications involved perform follow-up audits electronically. The department has accomplished these tasks not by purchasing an expensive software product, but by using existing software resources. The department cur-rently uses Microsoft Office for automating the creation and use of its workpapers; however, it developed this application before Microsoft Office was even a twinkle in Bill Gates' eye.

关键词：

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：