检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Shen, Junzhong Qiao, Yuran Huang, You Wen, Mei Zhang, Chunyuan College of Computer National University of Defense Technology Changsha410073 China National Key Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha410073 China

Large-scale floating-point matrix multiplication is a fundamental kernel in many scientific and engineering applications. Most existing work only focus on accelerating matrix multiplication on FPGA by adopting a linear systolic array. This paper towards the extension of this architecture by proposing a scalable and highly configurable multi-array architecture. In addition, we propose a work-stealing scheme to ensure the equality in the workload partition among multiple linear arrays. Furthermore, an analytical model is developed to determine the optimal design parameters. Experiments on a real-life convolutional neural network (CNN) show that we can obtain the optimal extension of the linear array architecture. Copyright © 2018, The Authors. All rights reserved.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Deep Discriminative Clustering Network

Deep Discriminative Clustering Network

引用

International Joint Conference on Neural Networks

作者： Xuying Shao Keshi Ge Huayou Su Lei Luo Baoyun Peng Dongsheng Li Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China

Deep clustering aims to cluster unlabeled data by embedding them into a subspace based on deep model. The key challenge of deep clustering is to learn discriminative representations for input data with high dimensions. In this paper, we present a deep discriminative clustering network for clustering the real-world images. We use a convolutional auto-encoder stacked with a softmax layer to predict clustering assignments. To learn a discriminative representations, the proposed approach adds discriminative loss as embedded regularization with relative entropy minimization. With the discriminative loss, the network can not only produce clustering assignments, but also learn discriminative features by reducing intra-cluster distance and increasing inter-cluster distance. We evaluate the proposed method on three datasets: MNIST-full, YTF and FRGC-v2.0. We outperform state-of-the-art results on MNIST-full and FRGC-v2.0 and achieve competitive result on YTF. The source code has been made publicly available at .

关键词： Machine learning Clustering algorithms Image reconstruction Linear programming Clustering methods Neural networks Task analysis

来源：评论

学校读者我要写书评

暂无评论

FD-MOBILENET: IMPROVED MOBILENET WITH A FAST DOWNSAMPLING STRATEGY

FD-MOBILENET: IMPROVED MOBILENET WITH A FAST DOWNSAMPLING ST...

引用

IEEE International Conference on Image processing

作者： Zheng Qin Zhaoning Zhang Xiaotao Chen Changjian Wang Yuxing Peng Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China

We present Fast-Downsampling MobileNet (FD-MobileNet), an efficient and accurate network for very limited computational budgets (e.g., 10-140 MFLOPs). Our key idea is applying a fast down-sampling strategy to MobileNet framework. In FD-MobileNet, we perform 32× downsampling within 12 layers, only half the layers in the original MobileNet. This design brings three advantages: (i) It remarkably reduces the computational cost. (ii) It increases the information capacity and achieves significant performance improvements. (iii) It is engineering-friendly and provides fast actual inference speed. Experiments on ILSVRC 2012 and PASCAL VOC datasets demonstrate that FD-MobileNet consistently outperforms MobileNet and achieves comparable results with ShuffleNet under different computational budgets, for instance, surpassing Mobile-Net by 5.5% on the ILSVRC 2012 top-1 accuracy and 8.3% on the VOC 2007 mAP under a complexity of 12 MFLOPs. On an ARM-based device, FD-MobileNet achieves 1.11× inference speedup over MobileNet and 1.82× over ShuffleNet under the same complexity.

关键词： Computer architecture Complexity theory Neural networks Training Hardware Computational modeling Standards

来源：评论

学校读者我要写书评

暂无评论

Meeting deadlines for approximation processing in MapReduce environments

引用

Frontiers of Information technology & Electronic Engineering 2017年第11期18卷 1754-1772页

作者： Ming-hao HU Chang-jian WANG Yu-xing PENG National Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha 410073 China

To provide timely results for big data analytics, it is crucial to satisfy deadline requirements for MapReduce jobs in today＇s production environments. Much effort has been devoted to the problem of meeting deadlines, and typically there exist two kinds of solutions. The first is to allocate appropriate resources to complete the entire job before the specified time limit, where missed deadlines result because of tight deadline constraints or lack of resources; the second is to run a pre-constructed sample based on deadline constraints, which can satisfy the time requirement but fail to maximize the volumes of processed data. In this paper, we propose a deadline-oriented task scheduling approach, named ＇Dart＇, to address the above problem. Given a specified deadline and restricted resources, Dart uses an iterative estimation method, which is based on both historical data and job running status to precisely estimate the real-time job completion time. Based on the estimated time, Dart uses an approach-revise algorithm to make dynamic scheduling decisions for meeting deadlines while maximizing the amount of processed data and mitigating stragglers. Dart also efficiently handles task failures and data skew, protecting its performance from being harmed. We have validated our approach using workloads from OpenCloud and Facebook on a cluster of 64 virtual machines. The results show that Dart can not only effectively meet the deadline but also process near-maximum volumes of data even with tight deadlines and limited resources.

关键词： MapReduce Approximation jobs Deadline Task scheduling Straggler mitigation

来源：评论

学校读者我要写书评

暂无评论

Design of an Indoor Exploration and Multi-Objective Navigation System

Design of an Indoor Exploration and Multi-Objective Navigati...

引用

第37届中国控制会议

作者： Guoxian Zheng Lei Zhang Huaxi (Yulin) Zhang Bo Ding State Key Laboratory of Synthetical Automation for Process Industries Northeastern University MIS and INSSET Universite de Picardie Jules Verne National Laboratory for Parallel and Distributed Processing National University of Defense Technology

In this paper,we propose an indoor robot autonomous navigation *** robot firstly explores in an unknown environment,and then navigates autonomously by using the explored *** robot is equipped a 2 D laser scanner as the main *** laser scanner is used for path planning and frontier-based exploration.A 2 D global occupancy map is built for path planning,frontier-based exploration and multi-objective autonomous *** scans are transmitted into Simultaneous Localization and Mapping（SLAM） process in the exploration *** indoor environment,the exploration efficiency is improved by merging a heuristic *** using multi-threading technology and a 3 D perception approach proposed in this paper,the robot equipped with a low-cost RGBD sensor can detect all kinds of obstacles to achieve highly reliable navigation in complicated 3 D ***,we develop a multi-objective navigation application to make human-robot interaction more convenient and satisfy multi-task *** approaches are demonstrated by experimental results.

关键词： Exploration Heuristic algorithm multi-threading technology 3D Perception Multi-objective navigation

来源：评论

学校读者我要写书评

暂无评论

Learning generic diffusion processes for image restoration

arXiv

引用

arXiv 2018年

作者： Qiao, Peng Dou, Yong Chen, Yunjin Feng, Wensen Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China ULSee Inc. Hangzhou China College of Computer Science & Software Engineering Shenzhen University Shenzhen China

Image restoration problems are typical ill-posed problems where the regularization term plays an important role. The regularization term learned via generative approaches is easy to transfer to various image restoration, but offers inferior restoration quality compared with that learned via discriminative approaches. On the contrary, the regularization term learned via discriminative approaches are usually trained for a specific image restoration problem, and fail in the problem for which it is not trained. To address this issue, we propose a generic diffusion process (genericDP) to handle multiple Gaussian denoising problems based on the Trainable Non-linear Reaction Diffusion (TNRD) models. Instead of one model, which consists of a diffusion and a reaction term, for one Gaussian denoising problem in TNRD, we enforce multiple TNRD models to share one diffusion term. The trained genericDP model can provide both promising denoising performance and high training efficiency compared with the original TNRD models. We also transfer the trained diffusion term to non-blind deconvolution which is unseen in the training phase. Experiment results show that the trained diffusion term for multiple Gaussian denoising can be transferred to image non-blind deconvolution as an image prior and provide competitive performance. Copyright © 2018, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

SAWSDL-iMatcher: A Customizable and Effective Semantic Web Service Matchmaker

SSRN

引用

SSRN 2018年

作者： Wei, Dengping Wang, Ting Wang, Ji Bernstein, Abraham National University of Defense Technology Changsha410073 China University of Zürich Binzmühlestrasse 14 ZürichCH-8050 Switzerland National Laboratory for Parallel and Distributed Processing Changsha410073 China Dynamic and Distributed Information Systems Group

As the number of publicly available services grows, discovering proper services becomes an important issue and has attracted amount of attempts. This paper presents a new customizable and effective matchmaker, called SAWSDL-iMatcher. It supports a matchmaking mechanism, named iXQuery, which extends XQuery with various similarity joins for SAWSDL service discovery. Using SAWSDL-iMatcher, users can flexibly customize their preferred matching strategies according to different application requirements. SAWSDL-iMatcher currently supports several matching strategies, including syntactic and semantic matching strategies as well as several statistical-model-based matching strategies which can effectively aggregate similarity values from matching on various types of service description information such as service name, description text, and semantic annotation. Besides, we propose a semantic matching strategy to measure the similarity among SAWSDL semantic annotations. These matching strategies have been evaluated in SAWSDL-iMatcher on SAWSDL-TC2 and Jena Geography Dataset (JGD). The evaluation shows that different matching strategies are suitable for different tasks and contexts, which implies the necessity of a customizable matchmaker. In addition, it also provides evidence for the claim that the effectiveness of SAWSDL service matching can be significantly improved by statistical-model-based matching strategies. Our matchmaker is competitive with other matchmakers on benchmark tests at S3 contest 2009. © 2018, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Sample dropout for audio scene classification using multi-scale dense connected convolutional neural network

arXiv

引用

arXiv 2018年

作者： Feng, Dawei Xu, Kele Mi, Haibo Liao, Feifan Zhou, Yan Science and Technology on Parallel and Distributed Laboratory School of Computer National University of Defense Technology Changsha410073 China School of Information and Communication National University of Defense Technology Wuhan430010 China

Acoustic scene classification is an intricate problem for a machine. As an emerging field of research, deep Convolutional Neural Networks (CNN) achieve convincing results. In this paper, we explore the use of multi-scale Dense connected convolutional neural network (DenseNet) for the classification task, with the goal to improve the clas-sification performance as multi-scale features can be extracted from the time-frequency representation of the audio signal. On the other hand, most of previous CNN-based audio scene classification approaches aim to improve the classification accuracy, by employing different regularization techniques, such as the dropout of hidden units and data augmentation, to reduce overfitting. It is widely known that outliers in the training set have a high negative inuence on the trained model, and culling the outliers may improve the classification performance, while it is often under-explored in previous studies. In this paper, inspired by the silence removal in the speech signal processing, a novel sample dropout approach is proposed, which aims to remove outliers in the training dataset. Using the DCASE 2017 audio scene classification datasets, the experimental results demonstrates the proposed multi-scale DenseNet providing a su-perior performance than the traditional single-scale DenseNet, while the sample dropout method can further improve the classification robustness of multi-scale DenseNet. Copyright © 2018, The Authors. All rights reserved.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

VirtMan:design and implementation of a fast booting system for homogeneous virtual machines in iVCE

引用

Frontiers of Information technology & Electronic Engineering 2016年第2期17卷 110-121页

作者： Zi-yang LI Yi-ming ZHANG Dong-sheng LI Peng-fei ZHANG Xi-cheng LU National Laboratory for Parallel and Distributed Processing School of ComputerNational University of Defense Technology

Internet-based virtual computing environment （iVCE） has been proposed to combine data centers and other kinds of computing resources on the Internet to provide efficient and economical services. Virtual machines （VMs） have been widely used in iVCE to isolate different users/jobs and ensure trustworthiness, but traditionally VMs require a long period of time for booting, which cannot meet the requirement of iVCE＇s large-scale and highly dynamic applications. To address this problem, in this paper we design and implement VirtMan, a fast booting system for a large number of virtual machines in iVCE. VirtMan uses the Linux Small Computer System Interface （SCSI） target to remotely mount to the source image in a scalable hierarchy, and leverages the homogeneity of a set of VMs to transfer only necessary image data at runtime. We have implemented VirtMan both as a standalone system and for OpenStack. In our 100-server testbed, VirtMan boots up 1000 VMs （with a 15 CB image of Windows Server 2008） on 100 physical servers in less than 120 s, which is three orders of magnitude lower than current public clouds.

关键词： Virtual machine Fast booting Homogeneity Internet-based virtual computing environment （iVCE）

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “A distributed Relation Detection Approach in the Internet of Things”

引用

Mobile Information Systems 2019年第1期2019卷

作者： Weiping Zhu Hongliang Lu Xiaohui Cui Jiannong Cao International School of Software Wuhan University Wuhan *** Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha *** Department of Computing Hong Kong Polytechnic University Kowloon Hong Kongpolyu.edu.hk

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：