检索结果-内蒙古大学图书馆

Accuracy evaluation of deep belief networks with fixed-point arithmetic

Computer Modelling and New Technologies 2014年第6期18卷 7-14页

作者： Jiang, Jingfei Hu, Rongdong Mikel, Lujan Dou, Yong Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology ChangSha Hunan China University of Manchester Manchester United Kingdom

Deep Belief Networks (DBNs) are state-of-art Machine Learning techniques and one of the most important unsupervised learning algorithms. Training DBNs is computationally intensive which naturally leads to investigate FPGA acceleration. Fixed-point arithmetic can be used when implementing DBNs in FPGAs to reduce execution time, but it is not clear the implications for accuracy. Previous studies have focused only on accelerators using some fixed bit-widths. A contribution of this paper is to demonstrate the bit-width effect on various configurations of DBNs in a comprehensive way by experimental evaluation. Explicit performance changing points are found using various bit-widths. The impact of sigmoid function approximation, required part of DBNs, is evaluated. A solution of mixed bit-widths DBN is proposed, fitting the bit-widths of FPGA primitives and gaining similar performance to the software implementation. Our results provide a guide to inform the design choices on bit-widths when implementing DBNs in FPGAs documenting clearly the trade-off in accuracy.

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

Synchronization Error Detection of MPI Programs by Symbolic Execution

Synchronization Error Detection of MPI Programs by Symbolic ...

引用

Asia-Pacific Conference on Software Engineering

作者： Xianjin Fu Zhenbang Chen Chun Huang Wei Dong Ji Wang College of Computer National University of Defense Technology Changsha China Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha China

ISBN: (纸本)9781479974276

Asynchrony based overlapping of computation and communication is commonly used in MPI applications. However, this overlapping introduces synchronization errors frequently in asynchronous MPI programming. In this paper, we propose a symbolic execution based method for detecting input-related synchronization errors. The path space of an MPI program is systematically explored, and the related operations of the synchronization errors in the program are checked specifically. In addition, two optimizations are proposed to improve the efficiency. We have implemented our method as a prototype tool based on the symbolic executor Cloud9. The results of the extensive experiments indicate the effectiveness of our method.

关键词： Synchronization Data communication Libraries Optimization Buffer storage Prototypes Schedules

来源：评论

学校读者我要写书评

暂无评论

Automatic Detecting Performance Bugs in Cloud Computing Systems via Learning Latency Specification Model

Automatic Detecting Performance Bugs in Cloud Computing Syst...

引用

2014 IEEE 8th International Symposium on Service Oriented System Engineering

作者： Haibo Mi Huaimin Wang Zhenbang Chen Yangfan Zhou Science and Technology on Parallel & Distributed Processing Laboratory National Univ. of Defense Technology Shenzhen Research Institute The Chinese Univ. of Hong Kong

Performance bugs that don't cause fail-stop errors but degradation of system performance have been one of the most fundamental issues in the production platform. How to effectively online detect bugs becomes more and more urgent for engineers. Performance bugs usually manifest themselves as the anomalous call structures of request traces or anomalous latencies of invoked methods. In this paper, we propose an automatic performance bug online detecting approach, CloudDoc. CloudDoc maintains a performance model mined from execution traces that are collected in the normal period. The performance model captures the characteristics of call structures of request traces together with corresponding latencies. With the performance model, CloudDoc periodically detects whether performance bugs occur or not. All suspicious call structures or latency-abnormal invoked methods are presented to engineers. We report two case studies to demonstrate the effectiveness of CloudDoc in helping engineers identify performance bugs.

关键词： Computer bugs Computational modeling Cloud computing Electronic mail Merging System performance Servers

来源：评论

学校读者我要写书评

暂无评论

Soft-Constrained Nonnegative Matrix Factorization via Normalization

Soft-Constrained Nonnegative Matrix Factorization via Normal...

引用

International Joint Conference on Neural Networks

作者： Long Lan Naiyang Guan Xiang Zhang Dacheng Tao Zhigang Luo Science and Technology on Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Centre for Quantum Computation & Intelligent Systems and the Faculty of Engineering and Information Technology University of Technology

ISBN: (纸本)9781479914821

Semi-supervised clustering aims at boosting the clustering performance on unlabeled samples by using labels from a few labeled samples. Constrained NMF (CNMF) is one of the most significant semi-supervised clustering methods, and it factorizes the whole dataset by NMF and constrains those labeled samples from the same class to have identical encodings. In this paper, we propose a novel soft-constrained NMF (SCNMF) method by softening the hard constraint in CNMF. Particularly, SCNMF factorizes the whole dataset into two lower-dimensional factor matrices by using multiplicative update rule (MUR). To utilize the labels of labeled samples, SCNMF iteratively normalizes both factor matrices after updating them with MURs to make encodings of labeled samples close to their label vectors. It is therefore reasonable to believe that encodings of unlabeled samples are also close to their corresponding label vectors. Such strategy significantly boosts the clustering performance even when the labeled samples are rather limited, e.g., each class owns only a single labeled sample. Since the normalization procedure never increases the computational complexity of MUR, SCNMF is quite efficient and effective in practices. Experimental results on face image datasets illustrate both efficiency and effectiveness of SCNMF compared with both NMF and CNMF.

关键词： Matrix decomposition Encoding Vectors Clustering methods Clustering algorithms Time complexity Face

来源：评论

学校读者我要写书评

暂无评论

Box-constrained Projective Nonnegative Matrix Factorization via Augmented Lagrangian Method

Box-constrained Projective Nonnegative Matrix Factorization ...

引用

International Joint Conference on Neural Networks

作者： Xiang Zhang Naiyang Guan Long Lan Dacheng Tao Zhigang Luo Science and Technology on Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Centre for Quantum Computation & Intelligent Systems and the Faculty of Engineering and Information Technology University of Technology

ISBN: (纸本)9781479914821

Projective non-negative matrix factorization (PNMF) projects a set of examples onto a subspace spanned by a non-negative basis whose transpose is regarded as the projection matrix. Since PNMF learns a natural parts-based representation, it has been successfully used in text mining and pattern recognition. However, it is non-trivial to analyze the convergence of the optimization algorithms for PNMF because its objective function is non-convex. In this paper, we propose a Box-constrained PNMF (BPNMF) method to overcome this deficiency of PNMF. In particular, BPNMF introduces an auxiliary variable, i.e., the coefficients of examples, and incorporates the following two types of constraints: 1) each entry of the basis is non-negative and upper-bounded, i.e., box-constrained, and 2) the coefficients equal to the projected points of the examples. The first box constraint makes the basis to be bound and the second equality constraint keeps its equivalence to PNMF. Similar to PNMF, BPNMF is difficult because the objective function is non-convex. To solve BPNMF, we developed an efficient algorithm in the frame of augmented Lagrangian multiplier (ALM) method and proved that the ALM-based algorithm converges to local minima. Experimental results on two face image datasets demonstrate the effectiveness of BPNMF compared with the representative methods.

关键词： Accuracy Linear programming Training Convergence Optimization Face Educational institutions

来源：评论

学校读者我要写书评

暂无评论

DKNNS:Scalable and accurate distributed K nearest neighbor search for latency-sensitive applications

引用

science China(Information sciences) 2013年第3期56卷 123-139页

作者： FU YongQuan WANG YiJie National Key Laboratory for Parallel and Distributed Processing School of Computer ScienceNational University of Defense Technology

To reduce the access latencies of end hosts,latency-sensitive applications need to choose suitably close service machines to answer the access requests from end *** K nearest neighbor search locates K service machines closest to end hosts,which can efficiently optimize the access latencies for end *** work has weakness in terms of the accuracy and *** to the scalable and accurate K nearest neighbor search problem,we propose a distributed K nearest neighbor search method called DKNNS in this *** machines are organized into a locality-aware multilevel *** first locates a service machine that starts the search process based on a farthest neighbor search scheme,then discovers K nearest service machines based on a backtracking approach within the proximity region containing the target in the latency *** analysis,simulation results and deployment experiments on the PlanetLab show that,DKNNS can determine K approximately optimal service machines,with modest completion time and query ***,DKNNS is also quite stable that can be used for reducing frequent searches by caching found nearest neighbors.

关键词： latency sensitive network applications K nearest neighbor search network coordinate

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Security of parallel Programs via Reducing Scheduling Space

Enhancing the Security of Parallel Programs via Reducing Sch...

引用

IEEE International Symposium on Dependable, Autonomic and Secure Computing (DASC)

作者： Xu Zhou Gen Li Kai Lu Shuangxi Wang School of Computer National University of Defense Technology Changsha PR China Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha PR China

parallel programs face a new security problem - concurrency vulnerability, which is caused by a special thread scheduling instead of inputs. In this paper, we propose to automatically fix concurrency vulnerabilities by reducing thread scheduling space. Our method is based on two observations. First, most concurrency vulnerabilities are caused by atomicity violation errors. Second, reducing thread scheduling space does not harm the correctness of the original program. We designed a prototype runtime system shield using deterministic multithreading techniques. Shield is designed to transparently run parallel programs and schedule threads in large instruction blocks to prevent atomicity violation at best effort. In case some concurrency vulnerabilities cannot be fixed by shield's scheduling reducing scheme, we also provide a remedy strategy by integrating shield with record&replay function, so that it can help programmers to analyze attacker's behavior for manually fixing.

关键词： Concurrent computing Instruction sets Scheduling Runtime Computer bugs Security Processor scheduling

来源：评论

学校读者我要写书评

暂无评论

A cooperative CSMA/CA MAC for channel-hopping rendezvous based cognitive radio networks

A cooperative CSMA/CA MAC for channel-hopping rendezvous bas...

引用

International Conference on Communications and Networking in China (CHINACOM)

作者： Quan Liu Gang Hu Xiaodong Wang Xingming Zhou Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha Hunan China Department of Network Engineering National University of Defense Technology Changsha Hunan China

ISBN: (纸本)9781479959716

Rendezvous problem is known as the fundamental issue in MAC design for cognitive radio networks (CRNs). With the concept of blind rendezvous, numerous channel-hopping sequence (CHS) based rendezvous schemes have been proposed to solve this problem. However, little attention is paid to the design of a CSMA/CA MAC based on these rendezvous schemes. In this paper, we propose a cooperative CSMA/CA MAC (named CoCH-CSMA/CA MAC) which tailors 802.11 distributed coordination function (DCF) to the slotted operation manner of existing CHS based rendezvous schemes. More importantly, the rendezvous de-synchronization problem is identified in MAC design based on these rendezvous schemes. To alleviate its impact on MAC performance, a cooperative control feedback scheme employing correlation-based signal detection is proposed to help secondary users avoid backoff misbehavior and improve networking performance (i.e., packet delivery delay and network throughput). Extensive simulations are conducted to prove the effectiveness of our MAC design.

关键词： Delays Multiaccess communication Correlation Radiation detectors IEEE 802.11 Standards Receivers

来源：评论

学校读者我要写书评

暂无评论

Assessing the Impact of Cascading Failures on the Interdomain Routing System of the Internet

引用

New Generation Computing 2014年第3期32卷 237-255页

作者： Liu, Yujing Peng, Wei Su, Jinshu Wang, Zhilin College of Computer National University of Defense Technology Hunan Changsha China College of Computer Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Hunan Changsha China Education Department National University of Defense Technology Hunan Changsha China

The Internet is a typical complex network, whose traffic load is controlled by the inter-domain routing system. Due to the co-location of data plane and control plane of Border Gateway Protocol, the survivability of inter-domain routing system is sensitive to severe congestion. Therefore, an initial outage may lead to a cascade of failures in the Internet. But the cascading failures on links are able to be automatically restored when the congestion is mitigated. In this paper, we propose a model - CAFEIN for characterizing this special process. Based on CAFEIN, we assess the difference of impact under intentional attacks and random breakdowns; identify the worst affected part of the Internet; and study the propagation of cascading failures. Through simulations, we find that the cascading failures bring a great deal of added burden to the routing system. However, the cascading effect is amplified globally when the relative capacity of links is very low. Moreover, the difference of impact between intentional attack and random breakdown is not as prominent as previous research due to the unique automatic-restoration process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Translation Non-negative Matrix Factorization with Fast Optimization

Translation Non-negative Matrix Factorization with Fast Opti...

引用

IEEE International Conference on Systems, Man, and Cybernetics

作者： Yuanyuan Wang Naiyang Guan Bin Mao Xuhui Huang Zhigang Luo Department of Basic Courses Army Officer Academy Science and Technology on Parallel and Distributed Processing Laboratory College of Computer Science National University of Defense Technology College of Science National University of Defense Technology College of Computer Science National University of Defense Technology

ISBN: (纸本)9781479938414

Non-negative matrix factorization (NMF) reconstructs the original samples in a lower dimensional space and has been widely used in pattern recognition and data mining because it usually yields sparse representation. Since NMF leads to unsatisfactory reconstruction for the datasets that contain translations of large magnitude, it is required to develop translation NMF (TNMF) to first remove the translation and then conduct a decomposition. However, existing multiplicative update rule based algorithm for TNMF is not efficient enough. In this paper, we reformulate TNMF and show that it can be efficiently solved by using the state-of-the-art solvers such as NeNMF. Experimental results on face image datasets confirm both efficiency and effectiveness of the reformulated TNMF.

关键词： Non-negative matrix factorization (NMF) Translation transformation NeNMF

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：