检索结果-内蒙古大学图书馆

Optimization and parallelization Single Particle Cryo-EM Software RELION with GPU

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2018年第2期55卷 409-417页

作者： Su, Huayou Wen, Wen Li, Dongsheng Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha410073 China

Single particle cryo-electron microscopy (cryo-EM) is one of the most important methods of macromolecular structure. RELION (regularized likelihood optimization) is an open-source computer program for the refinement of macromolecular structures by single-particle analysis of cryo-EM data. Due to its easy usage and high quality results, RELION has attracted a lot of attentions from researchers. However, the computation requirement of this program is too huge to solve some large molecular structures with CPU, which harpers the popularization of RELION. In this paper, we characterize the algorithm of RELION and parallelize it with GPU. Firstly, the mathematical theory, computer patterns and performance bottlenecks of RELION are analyzed comprehensively. Then, we optimize the program targeting at fine-grained many-core architecture processor, such as GPU. We propose an efficient multi-level parallel model to utilize the powerful computation capacity of many-core processor. In order to achieve high performance, we reconstruct the data structure for GPU continues memory access. To avoid the limitation of GPU memory size, we implement an adaptive framework. The experimental results show that the proposed GPU based algorithm can achieve good performance. When compared with the CPU implementation, the speedup ratio of the application is more than 36 times, while the speedup ratio of compute-intensive algorithm is about 75X. Moreover, the testing results on multi GPUs show that the GPU based implementation has good scalability. © 2018, science Press. All right reserved.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Attention-based fault-tolerant approach for multi-agent reinforcement learning systems

arXiv

引用

arXiv 2019年

作者： Geng, Mingyang Xu, Kele Li, Yiying Liu, Shuqi Ding, Bo Wang, Huaimin National Key Laboratory of Parallel and Distributed Processing College of Computer National University of Defense Technology Changsha410073 China National Key Laboratory of Big Data Management and Analysis Northeastern University Shenyang110000 China

The aim of multi-agent reinforcement learning systems is to provide interacting agents with the ability to collaboratively learn and adapt to the behavior of other agents. In many real-world applications, the agents can only acquire a partial view of the world. However, in realistic settings, one or more agents that show arbitrarily faulty or malicious behavior may suffice to let the current coordination mechanisms fail. In this paper, we study a practical scenario considering the security issues in the presence of agents with arbitrarily faulty or malicious behavior. Under these circumstances, learning an optimal policy becomes particularly challenging, even in the unrealistic case that an agent's policy can be made conditional upon all other agents' observations. To overcome these difficulties, we present an Attention-based Fault-Tolerant (FT-Attn) algorithm which selects correct and relevant information for each agent at every time-step. The multi-head attention mechanism enables the agents to learn effective communication policies through experience concurrently to the action policies. Empirical results have shown that FT-Attn beats previous state-of-the-art methods in some complex environments and can adapt to various kinds of noisy environments without tuning the complexity of the algorithm. Furthermore, FT-Attn can effectively deal with the complex situation where an agent needs to reach multiple agents' correct observation at the same time. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Surveying concurrency bug detectors based on types of detected bugs

引用

science China(Information sciences) 2017年第3期60卷 5-31页

作者： Zhendong WU Kai LU Xiaoping WANG Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology College of Computer National University of Defense Technology

Concurrency bugs widely exist in concurrent programs and have caused severe failures in the real world. Researchers have made significant progress in detecting concurrency bugs, which improves software reliability. In this paper, we survey the most up-to-date and well-known concurrency bug detectors. We categorize the existing detectors based on the types of concurrency bugs. Consequently, we analyze data race detectors, atomicity violation detectors, order violation detectors, and deadlock detectors, respectively. We also discuss some other techniques which are mostly related to concurrency bug detection, including schedule bounding techniques, interleaving optimizing techniques, path expanding techniques, and deterministic replay techniques. Additionally, we statistically analyze the reviewed detectors and get some interesting findings, for instance, nearly 86% of previous detectors focus on data races and atomicity violations, and dynamic approaches are popular(74%). We also discuss the limitations of previous detectors, finding that 91% of previous detectors suffer from false negatives and 64% of previous detectors suffer from runtime overhead. Based on the reviewed detectors and statistical analysis, we conclude some future research directions, including accuracy, performance,applicability, and integrality.

关键词： concurrency bug detection data race atomicity violation order violation deadlock

来源：评论

学校读者我要写书评

暂无评论

Density-Attentive Head Detector for Crowd Counting

Density-Attentive Head Detector for Crowd Counting

引用

International Conference on Data science and Business Analytics (ICDSBA)

作者： Ziyu Zhao Xingyu Shen Long Lan Xiaoyao Yin Xiang Zhang Yonggang Che Zhigang Luo College of Computer National University of Defense Technology Changsha China Institute for Quantum Information & State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China Science and Technology on Parallel and Distributed Processing National University of Defense Technology Changsha China

ISBN: (数字)9781728146447

ISBN: (纸本)9781728146454

In crowd counting, regression-based method shows better performance in extreme density scenes by introduces a density map. However, the regression-based method fails to locate the positions of each head, which significantly restricts its applications. Detection-based method counts each head with their accurate locations but works only in middle or low-level density scenes. In this paper, a joint learning method, named Density-attentive Head Detector (DAHD) is developed to overcome their respective shortcomings via a multi-task training procedure. Specifically, to guarantee the sensitivity of the detector to small or partially occluded heads, we carefully equip the detector with a density map which learned from regression module. Moreover, a novel Dilated Feature Pyramid Network (DFPN) is introduced to our method to enlarge the receptive field of convolutional kernel, bringing confirmative additional benefits to identify small heads. Experiments on the popular ShanghaiTech and Mall datasets confirm the improved performance of DAHD compared with the current detection-based approaches, and a comparable performance to regression-based approaches in term of counting.

关键词： Detectors Feature extraction Object detection Faces Kernel Training Task analysis

来源：评论

学校读者我要写书评

暂无评论

MixedCache: Enabling Flow Directed Rule-Caching Scheme based on Heterogeneous Cache for OpenFlow

引用

Journal of Physics: Conference Series 2020年第1期1693卷

作者： Jialun Yang Yi Yang Jiahao Liu Rulin Liu Peng Qiao Baosheng Wang College of Computer Science and Technology National University of Defense Technology Changsha 410073 China Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha 410073 China

OpenFlow switches in SDN use Multiple Flow Tables (MFTs) for fine-grained flow control. Commodity switches integrate hardware storage resources such as SRAM and TCAM to store flow tables to achieve high-speed lookups. Many increased flow tables are rapidly exhausting these hardware storage resources, which makes the switches have to balance high-speed search and massive storage. The rule-caching scheme is a popular method to solve this problem, which caches the most commonly used rules into hardware storage resources. The existing rule-caching schemes are based on single hardware storage resources, and they cannot flexibly adjust the caching strategy according to the traffic characteristics. Simultaneously, the deployed commodity switches face the problem of difficulty in changing the size of SRAM and TCAM. This paper innovatively proposes the MixedCache scheme, which makes full use of the hardware storage resources in the switch according to the skewed characteristics of network traffic. MixedCache stores the large flows in SRAM by exact match and stores the small flows in the TCAM by wildcard match. MixedCache does not need to change the size of the deployed switch hardware storage resources, but makes full use of existing resources. Compared with the rule-caching scheme based on the exact match, the cache hit rate can increase by up to 15.61%. Compared with the rule-caching scheme based on the wildcard match, the cache hit rate can increase by up to 29.69%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Character feature learning for named entity recognition

Character feature learning for named entity recognition

引用

作者： Zeng, Ping Tan, Qingping Zhang, Haoyu Meng, Xiankai Zhang, Zhuo Xu, Jianjun Lei, Yan College of Computer National University of Defense Technology Changsha China National Key Laboratory for Parallel and Distributed Processing Changsha China School of Software Engineering Chongqing University Chongqing China

The deep neural named entity recognition model automatically learns and extracts the features of entities and solves the problem of the traditional model relying heavily on complex feature engineering and obscure professional knowledge. This issue has become a hot topic in recent years. Existing deep neural models only involve simple character learning and extraction methods, which limit their capability. To further explore the performance of deep neural models, we propose two character feature learning models based on convolution neural network and long short-term memory network. These two models consider the local semantic and position features of word characters. Experiments conducted on the CoNLL-2003 dataset show that the proposed models outperform traditional ones and demonstrate excellent performance. © Copyright 2018 The Institute of Electronics Information and Communication Engineers.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Enhancing 2D Representation via Adjacent Views for 3D Shape Retrieval

Enhancing 2D Representation via Adjacent Views for 3D Shape ...

引用

International Conference on Computer Vision (ICCV)

作者： Cheng Xu Zhaoqun Li Qiang Qiu Biao Leng Jingfei Jiang School of Computer Science & Engineering Beihang University Duke University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beihang University National Laboratory for Parallel and Distributed Processing National University of Defense Technology

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Multi-view shape descriptors obtained from various 2D images are commonly adopted in 3D shape retrieval. One major challenge is that significant shape information are discarded during 2D view rendering through projection. In this paper, we propose a convolutional neural network based method, CenterNet, to enhance each individual 2D view using its neighboring ones. By exploiting cross-view correlations, CenterNet learns how adjacent views can be maximally incorporated for an enhanced 2D representation to effectively describe shapes. We observe that a very small amount of, e.g., six, enhanced 2D views, are already sufficient for a panoramic shape description. Thus, by simply aggregating features from six enhanced 2D views, we arrive at a highly compact yet discriminative shape descriptor. The proposed shape descriptor significantly outperforms state-of-the-art 3D shape retrieval methods on the ModelNet and ShapeNetCore55 benchmarks, and also exhibits robustness against object occlusion.

关键词： Shape Three-dimensional displays Correlation Two dimensional displays Feature extraction Solid modeling Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Correction to: A compressed matrix sequence method for solving normal equations of bundle adjustment

引用

Machine Vision and Applications 2021年第4期32卷 1-1页

作者： Peng, Jiaxin Liu, Jie Wei, Hua Laboratory of Software Engineering for Complex Systems School of Computer Science National University of Defense Technology Changsha China Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Changsha China Algorithm Lab Changsha Morale Network Technology Co. Ltd. Changsha China Water and Land Resources Research Center of the Middle Reaches of Yangtze River School of Resources Environment Science and Engineering Hubei University of Science and Technology Xianning China

A correction to this paper has been published: https://***/10.1007/s00138-021-01222-5

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding User Interests Acquisition in Personalized Online Course Recommendation

引用

Asia Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint Conference on Web and Big Data, APWeb-WAIM 2018

作者： Li, Xiao Wang, Ting Wang, Huaimin Tang, Jintao Information Center National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China National Key Laboratory of Parallel and Distributed Processing National University of Defense Technology Changsha China

ISBN: (纸本)9783030012977

MOOCs have attracted a large number of learners with different education background all over the world. Despite its increasing popularity, MOOCs still suffer from the problem of high drop-out rate. One important reason may be due to the difficulty in understanding learning demand and user interests. To helper users find the most suitable courses, personalized course recommendation technology has become a hot research topic in e-learning and data mining community. One of the keys to the success of personalized course recommendation is a good user modeling method. Previous works in course recommendation often focus on developing user modeling methodology which learns latent user interests from historic learning data. Recently, interactive course recommendation has become more and more popular. In this paradigm, recommender systems can directly query user interests through survey tables or questionnaires and thus the learned interests may be more accurate. In this paper, we study the user interest acquisition problem based on the interactive course recommendation framework (ICRF). Under this framework, we systematically discuss different settings on querying user interests. To reduce performance-cost score, we propose the ICRF user interest acquisition algorithm that combines representative sampling and interest propagation algorithm to acquire user interests in a cost-effective way. With extensive experiments on real-world MOOC course enrollment datasets, we empirically demonstrate that our selective acquisition strategy is very effective and it can reduce the performance-cost score by 30.25% compared to the traditional aggressive acquisition strategies. © 2018, Springer Nature Switzerland AG.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid architecture for high speed regular expression matching 1

引用

1st International Symposium on Mobile Internet Security, MobiSec 2016

作者： Xu, Chengcheng Zhao, Baokang Chen, Shuhui Su, Jinshu College of Computer National University of Defense Technology No. 137 Yanwachi Street ChangshaHunan410073 China National Key Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha410073 China

ISBN: (数字)9789811078507

ISBN: (纸本)9789811078491

Mobile devices play an important role in our everyday lives, but they also bring great security threats. Deep packet inspection (DPI) is one of the most efficient methods to detect the malicious information hidden in the mobile traffic, and regular expression matching is widely used in DPI for its powerful expressive ability. However, with the increasing complexity of regular expressions, traditional solutions cannot meet the requirements of both storage and high performance. In this paper, we propose a novel hybrid matching architecture and two-stage memory architecture for the state of the art hybrid FA to solve this problem. Experiment results confirm that our architecture is scalable to complex rule sets, and the matching performance outperforms state of the art memory centric solution by up to 15x. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Memory architecture

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：