检索结果-内蒙古大学图书馆

2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999

作者： Zadeh, Lotfi A. Graduate School and Direc. Berkeley Initiative in Soft Computing Computer Science Division Electronics Research Laboratory Department of Electrical Engineering and Computer Science University of California BerkeleyCA94720-1776 United States

来源：评论

学校读者我要写书评

暂无评论

Negatively correlated neural networks for classification

引用

Artificial Life and Robotics 1999年第4期3卷 255-259页

作者： Liu, Yong Yao, Xin Evolvable Systems Laboratory Computer Science Division Electrotechnical Laboratory Tsukuba Ibaraki Japan School of Computer Science The University of Birmingham Birmingham U.K.

This paper presents a new algorithm for designing neural network ensembles for classification problems with noise. The idea behind this new algorithm is to encourage different individual networks in an ensemble to learn different parts or aspects of the training data so that the whole ensemble can learn the whole training data better. Negatively correlated neural networks are trained with a novel correlation penalty term in the error function to encourage such specialization. In our algorithm, individual networks are trained simultaneously rather than independently or sequentially. This provides an opportunity for different networks to interact with each other and to specialize. Experiments on two real-world problems demonstrate that the new algorithm can produce neural network ensembles with good generalization ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Toward a common component architecture for high-performance scientific computing

Toward a common component architecture for high-performance ...

引用

International Symposium on High Performance Distributed computing

作者： R. Armstrong D. Gannon A. Geist K. Keahey S. Kohn L. McInnes S. Parker B. Smolinski Sandia National Laboratories USA Oak Ridge National Laboratory USA Advanced Computing Laboratory Los Alamos National Laboratory USA Center for Applied Scientific Computing Lawrence Livemore National Laboratory USA Mathematics and Computer Science Division Argonne National Laboratory USA Department of Computer Science University of Utah USA

Describes work in progress to develop a standard for interoperability among high-performance scientific components. This research stems from the growing recognition that the scientific community needs to better manage the complexity of multidisciplinary simulations and better address scalable performance issues on parallel and distributed architectures. The driving force for this is the need for fast connections among components that perform numerically intensive work and for parallel collective interactions among components that use multiple processes or threads. This paper focuses on the areas we believe are most crucial in this context, namely an interface definition language that supports scientific abstractions for specifying component interfaces and a port connection model for specifying component interactions.

关键词： Component architectures Scientific computing Laboratories Object oriented modeling computer science Parallel programming Yarn Context modeling Software systems Mathematics

来源：评论

学校读者我要写书评

暂无评论

A new direction in fuzzy logic-toward a computational theory of perceptions

A new direction in fuzzy logic-toward a computational theory...

引用

Conference of the North American Fuzzy Information Processing Society - NAFIPS

作者： L.A. Zadeh Berkeley Initiative in Soft Computing (BISC) Computer Science Division and the Electronics Research Laboratory Department of EECS University of California Berkeley CA USA

Perceptions play a pivotal role in human cognition. The ability to reason with perceptions underlies the remarkable human capability to perform a wide variety of physical and mental tasks without any measurements and any computations. Everyday examples of such tasks are parking a car, driving in city traffic, playing golf, cooking a meal and summarizing a story. In an essential way, the capability to perform these tasks is based on the brain's ability to manipulate perceptions-perceptions of time, distance, force, direction, speed, shape, color, likelihood, intent, truth and other attributes of physical and mental objects.

关键词： Fuzzy logic Humans Natural languages Cognition Performance evaluation Physics computing Cities and towns Shape Books Psychology

来源：评论

学校读者我要写书评

暂无评论

From computing with numbers to computing with words. manipulation of measurements to manipulation of perceptions

From computing with numbers to computing with words. manipul...

引用

Proceedings of the International Conference on Intelligent Processing and Manufacturing of Materials, IPMM

作者： L.A. Zadeh Professor in the Graduate School and Director Berkeley Initiative in Soft Computing (BISC) Computer Science Division and the Electronics Research Laboratory Department of Electrical Engineering and Computer Science University of California Berkeley CA USA

来源：评论

学校读者我要写书评

暂无评论

Data management for large-scale scientific computations in high performance distributed systems

Data management for large-scale scientific computations in h...

引用

International Symposium on High Performance Distributed computing

作者： A. Choudhary M. Kandemir H. Nagesh J. No X. Shen V. Taylor S. More R. Thakur Center for Parallel and Distributed Computing Department of Electrical and Computer Engineering Northwestern University Evanston IL USA Mathematics and Computer Science Division Argonne National Laboratory Argonne IL USA

With the increasing number of scientific applications manipulating huge amounts of data, effective data management is an increasingly important problem. Unfortunately, so far the solutions to this data management problem either require deep understanding of specific storage architectures and file layouts (as in high-performance file systems) or produce unsatisfactory I/O performance in exchange for ease-of-use and portability (as in relational DBMSs). In this paper we present a new environment which is built around an active meta-data management system (MDMS). The key components of our three-tiered architecture are user application, the MDMS, and a hierarchical storage system (HSS). Our environment overcomes the performance problems of pure database-oriented solutions, while maintaining their advantages in terms of ease-of-use and portability. The high levels of performance are achieved by the MDMS, with the aid of user-specified directives. Our environment supports a simple, easy-to-use yet powerful user interface, leaving the task of choosing appropriate I/O techniques to the MDMS. We discuss the importance of an active MDMS and show how the three components, namely application, the MDMS, and the HSS, fit together. We also report performance numbers from our initial implementation and illustrate that significant improvements are made possible without undue programming effort.

关键词： Large-scale systems Distributed computing High performance computing Data visualization Engineering management Concurrent computing Relational databases Art Data analysis Image analysis

来源：评论

学校读者我要写书评

暂无评论

Multivariate geographic clustering in a metacomputing environment using globus

Multivariate geographic clustering in a metacomputing enviro...

引用

1999 ACM/IEEE Conference on Supercomputing, SC 1999

作者： Mahinthakumar, G. Hoffman, Forrest M. Hargrove, William W. Karonis, Nicholas T. Oak Ridge National Laboratory Center for Computational Sciences P. O. Box 2008 Oak RidgeTN37831-6203 United States University of Tennessee Energy Environment Resources Center Systems Development Institute 10521 Research Drive KnoxvilleTN37932 United States High Performance Computing Laboratory Department of Computer Science Northern Illinois University DekalbIL60115 United States

ISBN: (纸本)1581130910

The authors present a metacomputing application of multivariate, nonhierarchical statistical clustering to geographic environmental data from the 48 conterminous United States in order to produce maps of regions of ecological similarity, called ecoregions. These maps represent finer scale regionalizations than do those generated by the traditional technique: an expert with a marker pen. Several variables (e.g., temperature, organic matter, rainfall etc.) thought to affect the growth of vegetation are clustered at resolutions as fine as one square kilometer (1 km2). These data can represent over 7.8 million map cells in an n-dimensional (n = 9 to 25) data space. A parallel version of the iterative statistical clustering algorithm is developed by the authors using the MPI (Message Passing Interface) message passing routines. The parallel algorithm uses a classical, self-scheduling, single-program, multiple data (SPMD) organization;performs dynamic load balancing for reasonable performance in heterogeneous metacomputing environments;and provides fault tolerance by saving intermediate results for easy restarts in case of hardware failure. The parallel algorithm was tested on various geographically distributed heterogeneous metacomputing configurations involving an IBM SP3™, an IBM SP2™, and two SGI Origin 2000™'s. The tests were performed with minimal code modification, and were made possible by Globus™ (a metacomputing software toolkit) and the Globus-enabled version of MPI (MPICH-G). Our performance tests indicate that while the algorithm works reasonably well under the metacomputing environment for a moderate number of processors, the communication overhead can become prohibitive for large processor configurations. © 1999 IEEE.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Fast statistical-based interconnect modeling using automatic differentiation

Fast statistical-based interconnect modeling using automatic...

引用

International Conference on Simulation of Semiconductor Processes and Devices (SISPAD)

作者： L. Roh C. Bischof N. Chang K. Lee V. Kanevsky O.S. Nakagawa Soo Young Oh Math and Computer Science Division Argonne National Laboratory Argonne IL USA Institute for Scientific Computing RWTH Aachen University Aachen Germany Hewlett Packard Laboratories Palo Alto CA USA

Automatic differentiation is a technique for computing derivatives accurately and efficiently with minimal human effort. We employed this technique to generate derivative information of FCAP2/3 programs that simulate the parasitic effects of interconnects. This derivative information is used in the statistical modeling of worst-case interconnect delays and on-chip crosstalks. The ADIC (Automatic Differentiation in C) tool generated new versions of FCAP2 and FCAP3 programs that compute both the original results and the derivative information. We report on the rise of automatic differentiation and divided difference approaches for computing derivatives for FCAP3 programs. The results show that ADIC-generated code computes derivatives more accurately, more robustly, and faster than the divided difference approach.

关键词： Laboratories Computational modeling Crosstalk Delay effects Parasitic capacitance Delay estimation computer science Scientific computing Humans Robustness

来源：评论

学校读者我要写书评

暂无评论

Multivariate Geographic Clustering in A Metacomputing Environment Using Globus

Multivariate Geographic Clustering in A Metacomputing Enviro...

引用

Supercomputing Conference

作者： G. Mahinthakumar F.M. Hoffman W.W. Hargrove N.T. Karonis Oak Ridge National Laboratory Center for Computational Sciences Oak Ridge TN USA Environmental Sciences Division Oak Ridge National Laboratory Oak Ridge TN USA Energy Environment and Resources Center Systems Development Institute University of Tennessee Knoxville TN USA High Performance Computing Laboratory Department of Computer Science Northern Illinois University Dekalb IL USA

The authors present a metacomputing application of multivariate, nonhierarchical statistical clustering to geographic environmental data from the 48 conterminous United States in order to produce maps of regions of ecological similarity, called ecoregions. These maps represent finer scale regionalizations than do those generated by the traditional technique: an expert with a marker pen. Several variables (e.g., temperature, organic matter, rainfall etc.) thought to affect the growth of vegetation are clustered at resolutions as fine as one square kilometer (1 km2). These data can represent over 7.8 million map cells in an n-dimensional (n = 9 to 25) data space. A parallel version of the iterative statistical clustering algorithm is developed by the authors using the MPI (Message Passing Interface) message passing routines. The parallel algorithm uses a classical, self-scheduling, single-program, multiple data (SPMD) organization; performs dynamic load balancing for reasonable performance in heterogeneous metacomputing environments; and provides fault tolerance by saving intermediate results for easy restarts in case of hardware failure. The parallel algorithm was tested on various geographically distributed heterogeneous metacomputing configurations involving an IBM SP3TM, an IBM SP2TM, and two SGI Origin 2000TM ’s. The tests were performed with minimal code modification, and were made possible by GlobusTM (a metacomputing software toolkit) and the Globus-enabled version of MPI (MPICH-G). Our performance tests indicate that while the algorithm works reasonably well under the metacomputing environment for a moderate number of processors, the communication overhead can become prohibitive for large processor configurations.

关键词： Metacomputing Message passing Parallel algorithms Testing Temperature Vegetation mapping Clustering algorithms Iterative algorithms Load management Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

A study of database system with KANSEI information

A study of database system with KANSEI information

引用

IEEE International Conference on systems, Man and Cybernetics

作者： K. Yoshida T. Kato T. Yanaru Department of Computer Science & Electronics Kyushu Institute of Technology Fukuoka Japan Intelligent Systems Division Electro Technical Laboratory Tsukuba Ibaraki Japan Department of Industrial and Systems Engineering Chuo University Bunkyo Tokyo Japan Department of Electrical Engineering Kyushu Institute of Technology Fukuoka Japan

These days, the development of computer devices leads to computer user explosion. On the other hand, conventional technology cannot handle user diversity, because the computer cannot treat each user's subjectivity. It is important to materialize techniques which can answer the user's subjective requests flexibly for the coming new media epoch. The article focuses on studying how subjective impressions are grounded in physical perceptions, especially in visual perception. We propose a model for subjectivity and physical perceptions, and give an example in an image database system.

关键词： Database systems Humans Space technology Multimedia databases Cities and towns Visual perception Image databases Information retrieval Multimedia systems Psychology

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：