检索结果-内蒙古大学图书馆

IEEE Transactions on Signal processing

作者： Scutari, Gesualdo Facchinei, Francisco Lampariello, Lorenzo Sardellitti, Stefania Song, Peiran School of Industrial Engineering Purdue University West-LafayetteIN47907 United States Department of Computer Control and Management Engineering University of Rome 'La Sapienza' Rome00184 Italy Department of Business Studies Roma Tre University Roma00154 Italy Department of Information Electronics and Telecommunications University of Rome 'La Sapienza' Rome00184 Italy School of Information and Communication Engineering Beijing Information Science and Technology University Beijing100101 China

In Part I of this paper, we proposed and analyzed a novel algorithmic framework for the minimization of a nonconvex objective function, subject to nonconvex constraints, based on inner convex approximations. This Part ii is devoted to the (nontrivial) application of the framework to the following relevant large-scale problems ranging from communications to machine learning: 1) (generalizations of) the rate profile maximization in MIMO interference broadcast networks; 2) the max-min fair multicast multigroup beamforming problem in a multicell environment; and 3) a general nonconvex constrained bi-criteria formulation for k-sparse variable selection in statistical learning; the two criteria are a nonconvex loss objective function, measuring the fitness of the model to data, and the latter is a nonconvex sparsity-inducing constraint in the general form of difference-of-convex (DC) functions, which allows to accomodate in a unified fashion convex and nonconvex surrogates of the 0function. The proposed algorithms outperform current state-of-the-art schemes for 1)-3) both theoretically and numerically. For instance, they are the first distributed schemes for the class of problems 1) and 2); and they also lead to subproblems enjoying closed form solutions. © 2016 IEEE.

关键词： Learning systems Artificial intelligence Beamforming Constrained optimization Multicasting Applications in communications Constrained nonconvex optimizations Interference networks Non convex objective functions Nonconvex optimization State of the art scheme Statistical learning Successive convex approximations

来源：评论

学校读者我要写书评

暂无评论

利用圖形處理器計算大規模基因關聯分析暨病理切片分析

利用圖形處理器計算大規模基因關聯分析暨病理切片分析

引用

作者：陳彥禎臺灣大學

学位级别：碩士

本论文是由两个研究主题构成，两个主题皆以图形处理器分析大量医学资料。第一部分：本研究以计算基因组关联分析为中心，发展出一个新的演算法，并实作在图形处理器上。基因组关联分析广泛的被运用在研究基因组和性状间的关系。本研究... 详细信息

本论文是由两个研究主题构成，两个主题皆以图形处理器分析大量医学资料。第一部分：本研究以计算基因组关联分析为中心，发展出一个新的演算法，并实作在图形处理器上。基因组关联分析广泛的被运用在研究基因组和性状间的关系。本研究在图形处理器上之实作可以大幅加速基因组关联分析的运算，并且拥有极佳的可扩展性。本研究的核心在加速基因组关联分析中最耗费时间的 P 值计算。利用此新演算法加速的图形处理器实作程式将提供基因研究员一个更好的工具，在数分钟内能完成数以百亿组基因组关联分析，并且由於其拥有高度可扩展性，此演算法能够在多片图形处理器系统上计算更庞大的资料。第二部分：病理切片是从病人患病处切下之组织细胞所做成的切片，病理切片在癌症诊断中占据着非常重要的地位，然而由於病理切片没有特定形状、颜色，加上其判断规则之繁复以及影像之大、资料收集之困难，如何让电脑自动判断病理切片至今仍是一项困难的挑战。本研究利用低解析度的影像片段作为判断标的，利用深度学习最後达成在判断前列腺病理切片格里森分数 3+3 及 4+4 有 95% 的准确率。

关键词：基因組關聯分析 p值病理切片前列腺癌神經網路圖形處理器平行計算

来源：评论

学校读者我要写书评

暂无评论

AdaLearner: An Adaptive distributed Mobile Learning System for Neural Networks 17

AdaLearner: An Adaptive Distributed Mobile Learning System f...

引用

IEEE/ACM 36th International Conference on Computer-Aided Design (ICCAD)

作者： Mao, Jiachen Qin, Zhuwei Xu, Zirui Nixon, Kent W. Chen, Xiang Li, Hai Chen, Yiran Duke Univ Durham NC 27706 USA George Mason Univ Fairfax VA 22030 USA

ISBN: (纸本)9781538630938

Neural networks hold a critical domain in machine learning algorithms because of their self-adaptiveness and state-of-the-art performance. Before the testing (inference) phases in practical use, sophisticated training (learning) phases are required, calling for efficient training methods with higher accuracy and shorter converging time. Many existing studies focus on the training optimization on high-performance servers or computing clusters, e.g. GPU clusters. However, training neural networks on resource-constrained devices, e.g. mobile platforms, is an important research topic barely touched. In this paper, we implement AdaLearneran-adaptive distributed mobile learning system for neural networks that trains a single network with heterogenous mobile resources under the same local network in parallel. To exploit the potential of our system, we adapt neural networks training phase to mobile device-wise resources and fiercely decrease the transmission overhead for better system scalability. On three representative neural network structures trained from two image classification datasets, AdaLearner boosts the training phase significantly. For example, on LeNet, 1.75-3.37x speedup is achieved when increasing the worker nodes from 2 to 8, thanks to the achieved high execution parallelism and excellent scalability.

关键词： Training Computational modeling Data models Neural networks Load modeling parallel processing Mobile communication

来源：评论

学校读者我要写书评

暂无评论

基于自定义RDD的海量遥感图像并行镶嵌方法

引用

地球信息科学学报 2017年第10期19卷 1346-1354页

作者：景维鹏霍帅起东北林业大学信息与计算机工程学院哈尔滨150040

图像镶嵌是遥感图像处理中的重要内容,在跨区域遥感图像分析中发挥重要作用。为了解决传统遥感图像并行算法中存在的计算节点利用率低、频繁数据I/O等问题,本文根据Spark分布式内存计算框架,充分利用Spark利于迭代数据处理的优势,提出... 详细信息

图像镶嵌是遥感图像处理中的重要内容,在跨区域遥感图像分析中发挥重要作用。为了解决传统遥感图像并行算法中存在的计算节点利用率低、频繁数据I/O等问题,本文根据Spark分布式内存计算框架,充分利用Spark利于迭代数据处理的优势,提出了一种基于Spark自定义RDD(弹性分布式数据集)的并行镶嵌方法。该方法首先在集群的多个节点上通过相位相关法执行图像重叠区域估计操作,从而提高了图像重叠区域估计的多节点并行计算;然后,通过重写Spark中RDD的compute和get Partitions方法,自定义针对遥感图像处理的RDD,并将图像镶嵌中的重叠区域估计、图像配准和图像融合3个关键步骤作为自定义RDD的Transformation类型的操作算子;最后,通过隐式转换创建自定义RDD,并调用自定义RDD的操作算子实现图像镶嵌的并行处理。实验结果表明,与传统基于MPI的并行镶嵌算法相比,该方法在保证图像镶嵌效果的基础上,能够有效提高大数据量的图像镶嵌效率。

关键词：遥感图像并行镶嵌 Spark 相位相关法自定义RDD

来源：评论

学校读者我要写书评

暂无评论

Derivation languages of splicing P systems 12th

Derivation languages of splicing P systems

引用

12th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2017

作者： Mahalingam, Kalpana Paul, Prithwineel Song, Bosheng Pan, Linqiang Subramanian, K.G. Department of Mathematics Indian Institute of Technology Madras Chennai600036 India Key Laboratory of Image Information Processing Intelligent Control of Education Ministry of China School of Automation Huazhong University of Science and Technology WuhanHubei430074 China School of Electric and Information Engineering Zhengzhou University of Light Industry ZhengzhouHenan450002 China Faculty of Science Liverpool Hope University LiverpoolL16 9JD United Kingdom

ISBN: (纸本)9789811071782

Labelled splicing P systems are distributed parallel computing models, where sets of strings that evolve by splicing rules are labelled. In this work, we consider labelled splicing systems with the following modifications: (i) The strings in the membranes are present in arbitrary number of copies;(ii) the rules in the regions are finite in number. Results on the language family generated by the labelled splicing system in comparison with the language families of the Chomsky hierarchy, including recursively enumerable languages, are obtained, by involving only either one or two membranes in the P systems considered. © Springer Nature Singapore Pte Ltd 2017.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Deeply supervised depth map super-resolution as novel view synthesis

arXiv

引用

arXiv 2018年

作者： Song, Xibin Dai, Yuchao Qin, Xueying School of Computer Science and Technology Shandong University China Baidu Research Beijing China National Engineering Laboratory of Deep Learning Technology and Application China Shaanxi Key Lab of Information Acquisition and Processing School of Electronics and Information Northwestern Polytechnical University School of Software Shandong University China

Deep convolutional neural network (DCNN) has been successfully applied to depth map super-resolution and outperforms existing methods by a wide margin. However, there still exist two major issues with these DCNN based depth map super-resolution methods that hinder the performance: i) The low-resolution depth maps either need to be up-sampled before feeding into the network or substantial deconvolution has to be used;and ii) The supervision (high-resolution depth maps) is only applied at the end of the network, thus it is difficult to handle large up-sampling factors, such as ×8;×16. In this paper, we propose a new framework to tackle the above problems. First, we propose to represent the task of depth map super-resolution as a series of novel view synthesis sub-tasks. The novel view synthesis sub-task aims at generating (synthesizing) a depth map from different camera pose, which could be learned in parallel. Second, to handle large up-sampling factors, we present a deeply supervised network structure to enforce strong supervision in each stage of the network. Third, a multi-scale fusion strategy is proposed to effectively exploit the feature maps at different scales and handle the blocking effect. In this way, our proposed framework could deal with challenging depth map super-resolution efficiently under large up-sampling factors (e.g.×8;×16). Our method only uses the low-resolution depth map as input, and the support of color image is not needed, which greatly reduces the restriction of our method. Extensive experiments on various benchmarking datasets demonstrate the superiority of our method over current state-of-the-art depth map super-resolution methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Hieroglyph: Locally-Sufficient Graph processing via Compute-Sync-Merge

Hieroglyph: Locally-Sufficient Graph Processing via Compute-...

引用

Proceedings of the 2017 ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems

作者： Ju, Xiaoen Jamjoom, Hani Shin, Kang G. University of Michigan Ann ArborMI United States IBM T.J. Watson Research Center Yorktown HeightsNY United States

ISBN: (纸本)9781450350327

Mainstream graph processing systems (such as Pregel [3] and PowerGraph [1]) follow the bulk synchronous parallel model. This design leads to the tight coupling of computation and communication, where no vertex can proceed to the next iteration of computation until all vertices have been processed in the current iteration and graph states have been synchronized across all hosts. This coupling of computation and communication incurs significant performance penalty. Fully decoupling computation from communication requires (i) restricted access to only local state during computation and (ii) independence of inter-host communication from computation. We call the combination of both conditions local sufficiency. Local sufficiency is not efficiently supported by state of the art. Synchronous systems, by design, do not support local sufficiency due to their intrinsic computation-communication coupling. Even systems that implement asynchronous execution only partially achieve local sufficiency. For example, PowerGraph's asynchronous mode satisfies local sufficiency by distributed scheduling. © 2017 Owner/Author.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A Hopf-Lax Formulation of the Eikonal Equation for parallel Redistancing and Oblique Projection

A Hopf-Lax Formulation of the Eikonal Equation for Parallel ...

引用

作者： Royston, Michael Wayne University of California Los Angeles

学位级别：Ph.D.

The level set method is one of the most useful algorithms for scientific computing problems that require computations over complex geometric domains. By representing geometry in terms of implicit functions defined over regular Cartesian grids, level set methods automatically capture a wide range of dynamic shapes and topology changes. They have gained wide adoption for problems in fluid dynamics, image processing, chip manufacturing, combustion, computer animation and many more. Dynamic changes in the geometry are automatically resolved by advecting the implicit function throughout a flow domain. However, it is typically necessary for the function describing the level set to have some important properties that the advection process does not preserve. One such property is that the gradient of the implicit function should have unit norm. Given this requirement, much research has been done on replacing an implicit function with a new function that preserves the old zero isocontour while satisfying the unit norm gradient constraint. This process is called redistancing and its solution satisfies the eikonal equation. Many methods currently exist to solve this problem. Fast marching and fast sweeping are the most popular redistancing methods due to their efficiency and relative simplicity. However, these methods require propagation of information from the zero-isocontour outwards, and this data dependence complicates efficient implementation on today’s multiprocessor hardware. Recently an interesting alternative view has been developed that utilizes ii the Hopf-Lax formulation of the solution to the eikonal equation. In this approach, the signed distance at an arbitrary point is obtained without the need of distance information from neighboring points. We extend the work of Lee et al. to redistance functions defined via interpolation over a regular grid. The grid-based definition is essential for practical application in level set methods. We demonstrate the effectiveness

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Approach for Large-Scale Scene image Retrieval Based on Improved parallel k-Means Algorithm in MapReduce Environment

引用

MATHEMATICAL PROBLEMS IN ENGINEERING 2016年第1期2016卷 1-17页

作者： Cao, Jianfang Wang, Min Shi, Hao Hu, Guohua Tian, Yun Xinzhou Teachers Univ Dept Comp Sci & Technol Xinzhou 034000 Peoples R China Taiyuan Univ Sci & Technol Sch Comp Sci & Technol Taiyuan 030024 Peoples R China

The rapid growth of digital images has caused the traditional image retrieval technology to be faced with new challenge. In this paper we introduce a new approach for large-scale scene image retrieval to solve the problems of massive image processing using traditional image retrieval methods. First, we improved traditional k-Means clustering algorithm, which optimized the selection of the initial cluster centers and iteration procedure. Second, we presented a parallel design and realization method for improved k-Means algorithm applied it to feature clustering of scene images. Finally, a storage and retrieval scheme for large-scale scene images was put forward using the large storage capacity and powerful parallel computing ability of the Hadoop distributed platform. The experimental results demonstrated that the proposed method achieved good performance. Compared with the traditional algorithms with single node architecture and parallel k-Means algorithm, the proposed method has obvious advantages for use in large-scale scene image data retrieval in terms of retrieval accuracy, retrieval time overhead, and computational performance (speedup and efficiency, sizeup, and scaleup), which is a significant improvement from applying parallel processing to intelligent algorithms with large-scale datasets.

关键词： image retrieval K-means clustering DIGITAL images image processing PROBLEM solving

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical distributed processing Framework for Big image Data

引用

IEEE Transactions on Big Data 2016年第4期2卷 297-309页

作者： Dong, Le Lin, Zhiyu Liang, Yan He, Ling Zhang, Ning Chen, Qi Cao, Xiaochun Izquierdo, Ebroul University of Electronic Science and Technology of China Chengdu611731 China China Academy of Engineering Physics Mianyang Sichuan621900 China Cyberspace Administration of the People's Republic of China Beijing100010 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100864 China Queen Mary University of London LondonE1 4NS United Kingdom

This paper introduces an effective processing framework nominated image Cloud processing (ICP) to powerfully cope with the data explosion in image processing field. While most previous researches focus on optimizing the image processing algorithms to gain higher efficiency, our work dedicates to providing a general framework for those image processing algorithms, which can be implemented in parallel so as to achieve a boost in time efficiency without compromising the results performance along with the increasing image scale. The proposed ICP framework consists of two mechanisms, i.e., Static ICP (SICP) and Dynamic ICP (DICP). Specifically, SICP is aimed at processing the big image data pre-stored in the distributed system, while DICP is proposed for dynamic input. To accomplish SICP, two novel data representations named P-image and Big-image are designed to cooperate with MapReduce to achieve more optimized configuration and higher efficiency. DICP is implemented through a parallel processing procedure working with the traditional processing mechanism of the distributed system. Representative results of comprehensive experiments on the challenging imageNet dataset are selected to validate the capacity of our proposed ICP framework over the traditional state-of-The-Art methods, both in time efficiency and quality of results. © 2015 IEEE.

关键词： MapReduce

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：