检索结果-内蒙古大学图书馆

Towards structured parallel computing on architecture-independent parallel algorithm design for distributed-memory architectures

引用

JOURNAL OF COMPUTER AND SYSTEM SCIENCES 1996年第1期53卷 112-128页

作者： Gao, F UNIV BRITISH COLUMBIA DEPT COMP SCI VANCOUVER BC V6T 1W5 CANADA

This paper introduces an architecture-independent, hierarchical approach to algorithm design on distributed-memory architectures, in contrast to the current trend of tailoring algorithms towards specific architectures. We show that, rather surprisingly, this new approach can achieve uniformity without sacrificing efficiency. In our framework, there are three levels of algorithm design: design of a network-independent algorithm in a network-independent programming environment, design of virtual networks (virtual architectures) for the algorithm, and design of emulations of the virtual networks on physical networks. In its organizational principle, this methodology is analogous to the abstract data structure approach to sequential algorithm design. We propose the following thesis: architecture-independent optimality can lead to portable optimality. Namely, a single network-independent algorithm, when optimized network-independently, with the support of properly chosen virtual networks, can be implemented on a wide spectrum of physical networks to achieve optimality on each of them with respect to both computation and communication, We illustrate this thesis with an analysis of the example of algorithm design for ordinary matrix multiplication. In a paper by Gao, a general theory of portable optimality of parallel algorithms is presented. Besides its implications to the methodology of parallel algorithm design, our framework also suggests new questions for theoretical research in parallel computation on interconnection networks. (C) 1996 Academic Press, Inc.

关键词： Communication Complexity Computation Complexity sequential algorithm Frameworks Communication Research simulating physical network ARCHITECTURE Parallel algorithms Theses algorithms Virtual networks PARALLEL PROCESSING (COMPUTERS) algorithm design optimality Matrix multiplication

来源：评论

学校读者我要写书评

暂无评论

Kernel methods for clustering:: Competitive learning and c-means

引用

INTERNATIONAL JOURNAL OF UNCERTAINTY FUZZINESS AND KNOWLEDGE-BASED SYSTEMS 2006年第4期14卷 481-493页

作者： Inokuchi, Ryo Miyamoto, Sadaaki Univ Tsukuba Doctoral Program Risk Engn Tsukuba Ibaraki 3058573 Japan Univ Tsukuba Dept Risk Engn Tsukuba Ibaraki 3058573 Japan

Recently kernel methods in support vector machines have widely been used in machine learning algorithms to obtain nonlinear models. Clustering is an unsupervised learning method which divides whole data set into subgroups, and popular clustering algorithms such as c-means are employing kernel methods. Other kernel-based clustering algorithms have been inspired from kernel c-means. However, the formulation of kernel c-means has a high computational complexity. This paper gives an alternative formulation of kernel-based clustering algorithms derived from competitive learning clustering. This new formulation obviously uses sequential updating or on-line learning to avoid high computational complexity. We apply kernel methods to related algorithms: learning vector quantization and self-organizing map. We moreover consider kernel methods for sequential c-means and its fuzzy version by the proposed formulation.

关键词： competitive learning clustering c-means learning vector quantization self-organizing map kernel method sequential algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimally computing the shortest weakly visible subedge of a simple polygon

引用

JOURNAL OF algorithmS 1996年第3期20卷 459-478页

作者： Chen, DZ Department of Computer Science and Engineering University of Notre Dame Notre Dame Indiana 46556

Given an n-vertex simple polygon P, the problem of computing the shortest weakly visible subedge of P is that of finding a shortest line segment s on the boundary of P such that P is weakly visible from s (if s exists). In this paper, we present new geometric observations that are useful for solving this problem. Based on these geometric observations, we obtain optimal sequential and parallel algorithms for solving this problem. Our sequential algorithm runs in O(n) time, and our parallel algorithm runs in O(log n) time using O(n/log n) processors in the CREW PRAM computational model. Using the previously best known sequential algorithms to solve this problem would take O(n(2)) time. We also give geometric observations that lead to extremely simple and optimal algorithms for solving, both sequentially and in parallel, the case of this problem where the polygons are rectilinear. (C) 1996 Academic Press, Inc.

关键词： Optimal algorithm Parallel prefix Visibility Edge Polygon Parallel algorithms Edge of a figure or solid LITAF gene sequential algorithm Line sections visibility Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Estimation of time-varying heat sources through inversion of a low order model built with the Modal Identification Method from in-situ temperature measurements

引用

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER 2010年第1-3期53卷 206-219页

作者： Girault, M. Videcoq, E. Petit, D. ENSMA CNRS Lab Etud Therm UMR 6608 F-86961 Futuroscope France LMEE F-91020 Evry France

An approach using an experimentally built low-order model is proposed for the estimation of time-varying heat sources. In a first step, a low order dynamical system of equations, linking up temperatures at a set of specific points to heat sources strengths, is identified from experimental data using the Modal Identification Method. In a second step, the low order model is used to efficiently solve the transient inverse problem for the estimation of heat sources intensities from temperature measurements. The proposed approach is illustrated with an experimental set-up involving thermal diffusion with convective and radiative boundary conditions. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Nonlinear heat transfer Reduced model Experimental identification Inverse problem sequential algorithm Future time steps

来源：评论

学校读者我要写书评

暂无评论

Resolution of linear inverse forced convection problems using model reduction by the Modal Identification Method: application to turbulent flow in parallel-plate duct

引用

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER 2004年第17-18期47卷 3909-3925页

作者： Girault, M Petit, D Univ Poitiers Lab Etud Therm CNRS UMR 6608ENSMA F-86961 Futuroscope France

Inverse Heat Convection Problems have received attention only recently. They usually involve the use of a high order model corresponding to the spatial discretization of the domain. In this numerical study, the possibility to quickly solve such a problem with a low order model is analysed. The proposed method can be applied to any forced convection problem, whatever the geometry, as far as it is linear. Starting from a Detailed Model (DM) of the system, the Modal Identification Method is applied to build a Reduced Model (RM), which can be used to solve the inverse problem. The inversion procedure is sequential and requires no iterations. The function specification method is used to stabilize the inverse problem. An illustrative application is given. Turbulent forced convection is considered, with a hydrodynamically fully developed, thermally developing, incompressible, turbulent flow of a newtonian and constant property fluid inside a parallel-plate duct. Axial conduction in the flow is neglected. Two wall heat flux densities, varying with time, are estimated from the knowledge of simulated transient temperature measurements inside the fluid. When solving the inverse problem with RM instead of DM, a drastic reduction of computing time is obtained (with a reduction factor up to 11,000 in the present study), without significant loss of accuracy. Effects of functional form of the unknowns, sensors number and position, measurement error, on the accuracy of estimates are examined. (C) 2004 Elsevier Ltd. All rights reserved.

关键词： forced convection modal identification Reduced Model inverse method estimation of boundary conditions sequential algorithm Future Time Steps

来源：评论

学校读者我要写书评

暂无评论

FINDING A CLOSEST VISIBLE VERTEX PAIR BETWEEN 2 POLYGONS

引用

algorithmICA 1995年第2期14卷 183-201页

作者： AMATO, NM Department of Computer Science Texas A&M University College Station USA

Given nonintersecting simple polygoris P and Q, two vertices p is an element of P and q is an element of Q are said to be visible if pq does not properly intersect P or Q. We present a parallel algorithm for finding a... 详细信息

Given nonintersecting simple polygoris P and Q, two vertices p is an element of P and q is an element of Q are said to be visible if <($$)over bar>pq does not properly intersect P or Q. We present a parallel algorithm for finding a closest pair among all visible pairs (p,q) p is an element of P and q is an element of Q. The algorithm runs in time O(log n) using O(n) processors on a CREW PRAM, where n = \P\+\Q\. This algorithm can be implemented serially in O(n) time, which gives a new optimal sequential solution for this problem.

关键词： VISIBLE VERTEX DISTANCE SIMPLE POLYGON PARALLEL algorithm PRAM sequential algorithm

来源：评论

学校读者我要写书评

暂无评论

Defect chemistry modelling of oxygen-stoichiometry, vacancy concentrations, and conductivity of (La_1-xSr_x)_yMnO_3±δ

引用

SOLID STATE IONICS 2000年第1-4期129卷 145-162页

作者： Poulsen, FW Riso Natl Lab Dept Mat Res DK-4000 Roskilde Denmark

Two precise algorithms are devised for the calculation of defect concentrations in A-site acceptor doped ABO(3) perovskites. The two models contain nine species including cation vacancies on the A- and B-site. The small polaron model is based on three redox levels of the B-ion. A large polaron model, based on delocalised electrons, electron holes and all B-ions being trivalent is given in Appendix A. The sequential mathematical method allows us to calculate the high temperature oxygen partial pressure dependent properties of (La1-xSrx)(y)MnO3+/-delta in a unified manner irrespective of the type of defect regime, Simulations are shown for a pO(2) span from 10(-30) to 10(5) atm. The three required equilibrium constants for (La1-xSrx)(y)MnO3+/-delta had to be changed significantly from values given in literature in order to match the observed stoichiometry span. The main results shown are calculated by the small polaron model containing only ionic species - the B-ion may be Mn-B' (Mn2+), Mn-B(x) (Mn3+), and Mn-B(Mn4+). The A/B-ratio = y greatly influences the oxygen stoichiometry, oxygen ion vacancy- and cation vacancy concentrations and the total conductivity. Calculations are given for the range 0.87 less than or equal to y less than or equal to 1.13 for a Sr doping of 10% at 1000 degrees C. The defect model can simultaneously describe the observed stoichiometry and conductivity dependence on pO(2), if the electronic mobility is decreased by up to 50% at pO(2) < 10(-10) and pO(2) > 10(-2) arm. (C) 2000 Elsevier Science B.V. All rights reserved.

关键词： conductivity defect modelling LSM non stoichiometry perovskite sequential algorithm

来源：评论

学校读者我要写书评

暂无评论

FAST STRING-MATCHING algorithmS FOR RUN-LENGTH CODED STRINGS

引用

COMPUTING 1995年第2期54卷 119-125页

作者： CHUNG, KL National Taiwan Institute of Technology

Given a run-length coded text of length 2n and a run-length coded pattern of length 2m, m much less than n commonly, this paper first presents an O(n+m) time sequential algorithm for string matching, then presents an ... 详细信息

关键词： KNUTH-MORRIS-PRATT algorithm MESH WITH A RECONFIGURABLE BUS SYSTEM PARALLEL algorithm RUN-LENGTH CODING sequential algorithm STRING MATCHING

来源：评论

学校读者我要写书评

暂无评论

Decomposition methods for differentiable optimization problems over Cartesian product sets

引用

COMPUTATIONAL OPTIMIZATION AND APPLICATIONS 1998年第1期9卷 5-42页

作者： Patriksson, M Univ Washington Dept Math Seattle WA 98195 USA

This paper presents a unified analysis of decomposition algorithms for continuously differentiable optimization problems defined on Cartesian products of convex feasible sets. The decomposition algorithms are analyzed using the framework of cost approximation algorithms. A convergence analysis is made for three decomposition algorithms: a sequential algorithm which extends the classical Gauss-Seidel scheme, a synchronized parallel algorithm which extends the Jacobi method, and a partially asynchronous parallel algorithm. The analysis validates inexact computations in both the subproblem and line search phases, and includes convergence rate results. The range of feasible step lengths within each algorithm is shown to have a direct correspondence to the increasing degree of parallelism and asynchronism, and the resulting usage of more outdated information in the algorithms.

关键词： Cartesian product sets decomposition cost approximation sequential algorithm parallel processing partially asynchronous algorithms

来源：评论

学校读者我要写书评

暂无评论

Estimating Heavy-Tail Exponents Through Max Self-Similarity

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2011年第3期57卷 1615-1636页

作者： Stoev, Stilian A. Michailidis, George Taqqu, Murad S. Univ Michigan Dept Stat Ann Arbor MI 48109 USA Boston Univ Dept Math Boston MA 02215 USA

In this paper, a novel approach to the problem of estimating the heavy-tail exponent alpha > 0 of a distribution is proposed. It is based on the fact that block-maxima of size m scale at a rate m(1/alpha) for independent, as well as for a number of dependent data. This scaling rate can be captured well by the max-spectrum plot of the data that leads to regression based estimators for alpha . Consistency and asymptotic normality of these estimators is established for independent data under mild conditions on the behavior of the tail of the distribution. The proposed estimators have an important computational advantage over existing methods;namely, they can be calculated and updated sequentially in an on-line fashion without having to store the entire data set. Practical issues on the automatic selection of tuning parameters for the estimators and corresponding confidence intervals are also addressed. Extensive numerical simulations show that the proposed method is competitive for both small and large sample sizes, robust to contaminants and continues to work under the presence of substantial amount of dependence. The proposed estimators are used to illustrate the close connection between long-range dependence and heavy tails over an Internet traffic trace.

关键词： Block-maxima Frechet distribution heavy-tail exponent hill plot sequential algorithm

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：