检索结果-内蒙古大学图书馆

Optimization approaches of organizing streams on imagine processor

Jisuanji Xuebao/Chinese Journal of Computers 2008年第7期31卷 1092-1100页

作者： Yang, Xue-Jun Zeng, Li-Fang Deng, Yu Tang, Yu-Hua National Key Laboratory of Parallel and Distributed Processing School of Computer Science National University of Defense Technology Changsha 410073 China Jiangnan Remote Sensing Institute Shanghai 200072 China

Due to the characteristics of stream applications and the insufficiency of conventional processors when running stream programs, stream processors which support data-level parallelism become the research hotspot. This paper presents two means, stream partition (SP) and stream compression (SC), to optimize streams on Imagine. The results of simulation show that SP and SC can make stream applications take full advantage of the parallel clusters, pipelines and three-level memory hierarchy of the Imagine processor, and then reduce the execution time of stream programs.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Underwater acoustic classification using masked modeling-based swin transformer

引用

The Journal of the Acoustical Society of America 2022年第4_SUPPLEMENT期152卷 A296-A296页

作者： Kang you Kele Xu Ming Feng Boqing Zhu Tonguing Univ. Shanghai China National Key Lab. of Parallel and Distributed Processing (PDL) Changsha China 107 Yanwachi Changsha 410073 China kelele.xu@*** National Key Lab. of Parallel and Distributed Processing (PDL) Changsha China Changsha China

Underwater acoustic classification is a challenging task due to complex background noise and complicated sound propagation patterns. How to represent the signals is important for the classification task. In this paper, we propose a novel representation learning method for the underwater acoustic signals, leveraging the mask modeling-based self-supervised learning paradigm. Specifically, we first explore modifying the Swin Transformer architecture to learn general representation for the audio signals, accompanied with random masking on the log-mel spectrogram. The main goal of the pretext task is to predict the masked parts of Log-mel spectrogram and the gamma-stone spectrogram, so that the model can not only learn the local and global features but also learn complementary information. For downstream task, we utilize the labelled datasets to fine-tune the pre-trained model. On DeepShip datasets which consist of 47 hand 4 minof ship sounds in four categories, our model achieves state-of-the-art performance compared with competitive approaches. Our method obtains a classification accuracy of 78.03%, which is better than the separable convolution autoencoder (SCAE) and using the constant-Q transform spectrogram. This work demonstrates the potential of the masked modeling based self-supervised learning for understanding and interpretation of underwater acoustic signals.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scalable unbiased sampling method based on multi-peer adaptive random walk

引用

Ruan Jian Xue Bao/Journal of Software 2009年第3期20卷 630-643页

作者： Fu, Yong-Quan Wang, Yi-Jie Zhou, Jing National Key Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha 410073 China Staff Room of Computer Command Academy of the Corps of Engineers Xuzhou 221000 China

To deal with the scalable and fast unbiased sampling problems in unstructured P2P systems, a sampling method based on multi-peer adaptive random walk (SMARW) is proposed. In the method, based on the multi-peer random walk process, a set of provisional peers are selected as agents which start the sampling processes, by which the sampling process is speeded up with receiving a set of tunable number samples each time;Meanwhile, after receiving new samples earlier agents are replaced with these new samples which repeat the sampling process. With this simple replacement, it can be guaranteed with high probability that the system can reach the optimal load balance;furthermore, SMARW adopts an adaptive distributed random walk adjustment process to increase the convergence rate of the sampling process. A detailed theorical analysis and performance evaluation confirm that SMARW has a high level of unbiased sampling and near-optimal load balancing capability. © by Institute of Software, the Chinese Academy of Sciences. All rights reserved.

关键词： Peer to peer networks

来源：评论

学校读者我要写书评

暂无评论

Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable Neurons

arXiv

引用

arXiv 2022年

作者： Jin, Haibo Chen, Ruoxi Zheng, Haibin Chen, Jinyin Cheng, Yao Yu, Yue Liu, Xianglong College of Information Engineering Zhejiang University of Technology Hangzhou China Institute of Cyberspace Security Zhejiang University of Technology Hangzhou China Huawei International Singapore National Laboratory for Parallel and Distributed Processing College of Computer National University of Defense Technology Changsha China State Key Laboratory of Software Development Environment Beihang University Beijing China

Despite impressive capabilities and outstanding performance, deep neural networks (DNNs) have captured increasing public concern about their security problems, due to their frequently occurred erroneous behaviors. Therefore, it is necessary to conduct a systematical testing for DNNs before they are deployed to real-world applications. Existing testing methods have provided fine-grained metrics based on neuron coverage and proposed various approaches to improve such metrics. However, it has been gradually realized that a higher neuron coverage does not necessarily represent better capabilities in identifying defects that lead to errors. Besides, coverage-guided methods cannot hunt errors due to faulty training procedure. So the robustness improvement of DNNs via retraining by these testing examples are unsatisfactory. To address this challenge, we introduce the concept of excitable neurons based on Shapley value and design a novel white-box testing framework for DNNs, namely DeepSensor. It is motivated by our observation that neurons with larger responsibility towards model loss changes due to small perturbations are more likely related to incorrect corner cases due to potential defects. By maximizing the number of excitable neurons concerning various wrong behaviors of models, DeepSensor can generate testing examples that effectively trigger more errors due to adversarial inputs, polluted data and incomplete training. Extensive experiments implemented on both image classification models and speaker recognition models have demonstrated the superiority of DeepSensor. Compared with the state-of-the-art testing approaches, DeepSensor can find more test errors due to adversarial inputs (∼ ×1.2), polluted data (∼ ×5) and incompletely-trained DNNs (∼ ×1.3). Additionally, it can help DNNs build larger l2-norm robustness bound (∼ ×3) via retraining according to CLEVER's certification. We further provide interpretable proofs for effectiveness of DeepSensor via excitable neuro

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

TRANSDUCTIVE NONNEGATIVE MATRIX FACTORIZATION FOR SEMI-SUPERVISED HIGH-PERFORMANCE SPEECH SEPARATION

TRANSDUCTIVE NONNEGATIVE MATRIX FACTORIZATION FOR SEMI-SUPER...

引用

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Naiyang Guan Long Lan Dacheng Tao Zhigang Luo Xuejun Yang Science and Technology on Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Changsha Hunan 410073 China Centre for Quantum Computation and Intelligent Systems FEIT University of Technology Sydney Sydney NSW 2007 Australia State Key Laboratory of High Performance Computing National University of Defense Technology Changsha Hunan 410073 China

ISBN: (纸本)9781479928941

Regarding the non-negativity property of the magnitude spectrogram of speech signals, nonnegative matrix factorization (NMF) has obtained promising performance for speech separation by independently learning a dictionary on the speech signals of each known speaker. However, traditional NM-F fails to represent the mixture signals accurately because the dictionaries for speakers are learned in the absence of mixture signals. In this paper, we propose a new transductive NMF algorithm (TNMF) to jointly learn a dictionary on both speech signals of each speaker and the mixture signals to be separated. Since TNMF learns a more descriptive dictionary by encoding the mixture signals than that learned by NMF, it significantly boosts the separation performance. Experiments results on a popular TIMIT dataset show that the proposed TNMF-based methods outperform traditional NMF-based methods for separating the monophonic mixtures of speech signals of known speakers.

关键词： Speech Dictionaries as Topic Loudspeakers NMF protocol signals mixtures factorization HIGH-PERFORMANCE

来源：评论

学校读者我要写书评

暂无评论

FCloudless: A Performance-Aware Collaborative Mechanism for JointCloud Serverless

FCloudless: A Performance-Aware Collaborative Mechanism for ...

引用

IEEE International Conference on Joint Cloud Computing (JCC)

作者： Jianfei Liu Huaimin Wang Peichang Shi Yaojie Li Penghui Ma Guodong Yi National Key Laboratory of Parallel and Distributed Computing College of Computer Science National University of Defense Technology Changsha 410073 China Key Laboratory of Software Engineering for Complex Systems College of Computer Science National University of Defense Technology Changsha 410073 China Xiangjiang Lab Changsha 410073 China School of Advanced Interdisciplinary Studies Hunan University Of Technology and Business Changsha 410073 China

As a new stage in the development of the cloud computing paradigm, serverless computing has the high-level abstraction characteristic of shielding underlying details. This makes it extremely challenging for users to choose a suitable serverless platform. To address this, targeting the jointcloud computing scenario of heterogeneous serverless platforms across multiple clouds, this paper presents a jointcloud collaborative mechanism called FCloudless with cross-cloud detection of the full lifecycle performance of serverless platforms. Based on the benchmark metrics set that probe performance critical stages of the full lifecycle, this paper proposes a performance optimization algorithm based on detected performance data that takes into account all key stages that affect the performance during the lifecycle of a function and predicts the overall performance by combining the scores of local stages and dynamic weights. We evaluate FCloudless on AWS, AliYun, and Azure. The experimental results show that FCloudless can detect the underlying performance of serverless platforms hidden in the black box and its optimization algorithm can select the optimal scheduling strategy for various applications in a jointcloud environment. FCloudless reduces the runtime by 23.3% and 24.7% for cold and warm invocations respectively under cost constraints.

关键词：

来源：评论

学校读者我要写书评

暂无评论

科学研究的第五范式——以智能驱动的材料设计为例

引用

Engineering 2023年第5期24卷 126-137,I0003,I0004页

作者： Can Leng Zhuo Tang Yi-Ge Zhou Zean Tian Wei-Qing Huang Jie Liu Keqin Li Kenli Li Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangsha 410073China Laboratory of Software Engineering for Complex Systems National University of Defense TechnologyChangsha 410073China National Supercomputing Center in Changsha Changsha 410082China College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China Institute of Chemical Biology and Nanomedicine State Key Laboratory of Chemo/Biosensing and ChemometricsCollege of Chemistry and Chemical EngineeringHunan UniversityChangsha 410082China Department of Applied Physics School of Physics and ElectronicsHunan UniversityChangsha 410082China Department of Computer Science State University of New YorkNew PaltzNY 12561USA

科学正在进入一个新时代——第五范式——它被认为是知识整合到不同领域的主要特征,是基于无所不在的机器学习系统的计算社区中智能驱动的工作。在此,我们通过在天河一号超级计算机系统上构建的催化材料专门设计的典型平台案例,生动地... 详细信息

科学正在进入一个新时代——第五范式——它被认为是知识整合到不同领域的主要特征,是基于无所不在的机器学习系统的计算社区中智能驱动的工作。在此,我们通过在天河一号超级计算机系统上构建的催化材料专门设计的典型平台案例,生动地阐明了第五范式的本质,旨在促进第五范式在其他领域的培养。第五范式平台主要包括模型自动构建(原始数据提取)、指纹自动构建(神经网络特征选择)以及跨学科知识串联的重复迭代(“火山图”)。与分解一起进行的是对迭代中实现的体系结构的性能评估。通过讨论,第五范式的智能驱动平台可以极大地简化和改进研究中极其繁琐和具有挑战性的工作,并通过补偿机器学习中缺少样本和替代一些由于计算资源不足而导致的数值计算来实现数值计算与机器学习之间的相互反馈,从而加速探索过程。在数据驱动的学科中,跨学科专家的协同作用和对动态数据需求的急剧增长仍然是一个挑战。我们相信,对第五范式平台的一瞥可以为其在其他领域的应用铺平道路。

关键词：机器学习自动构建天河一号数据驱动神经网络动态数据知识整合科学研究

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning for combinatorial optimization: Covering salesman problems

arXiv

引用

arXiv 2021年

作者： Li, Kaiwen Zhang, Tao Wang, Rui Wang, Yuheng Han, Yi College of Systems Engineering National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology HKL-MSI2T Changsha410073 China Graduate College National University of Defense Technology Changsha410073 China Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Changsha410073 China

This paper introduces a new deep learning approach to approximately solve the Covering Salesman Problem (CSP). In this approach, given the city locations of a CSP as input, a deep neural network model is designed to directly output the solution. It is trained using the deep reinforcement learning without supervision. Specifically, in the model, we apply the Multi-head Attention to capture the structural patterns, and design a dynamic embedding to handle the dynamic patterns of the problem. Once the model is trained, it can generalize to various types of CSP tasks (different sizes and topologies) with no need of re-training. Through controlled experiments, the proposed approach shows desirable time complexity: it runs more than 20 times faster than the traditional heuristic solvers with a tiny gap of optimality. Moreover, it significantly outperforms the current state-of-the-art deep learning approaches for combinatorial optimization in the aspect of both training and inference. In comparison with traditional solvers, this approach is highly desirable for most of the challenging tasks in practice that are usually large-scale and require quick decisions. Copyright © 2021, The Authors. All rights reserved.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement

arXiv

引用

arXiv 2022年

作者： Yang, Yuting Huang, Pei Cao, Juan Li, Jintao Lin, Yun Dong, Jin Song Ma, Feifei Zhang, Jian Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Beijing China National University of Singapore Singapore Laboratory of Parallel Software and Computational Science ISCAS Beijing China

Recent years have seen the wide application of NLP models in crucial areas such as finance, medical treatment, and news media, raising concerns of the model robustness and vulnerabilities. In this paper, we propose a novel prompt-based adversarial attack to compromise NLP models and robustness enhancement technique. We first construct malicious prompts for each instance and generate adversarial examples via mask-and-filling under the effect of a malicious purpose. Our attack technique targets the inherent vulnerabilities of NLP models, allowing us to generate samples even without interacting with the victim NLP model, as long as it is based on pre-trained language models (PLMs). Furthermore, we design a prompt-based adversarial training method to improve the robustness of PLMs. As our training method does not actually generate adversarial samples, it can be applied to large-scale training sets efficiently. The experimental results show that our attack method can achieve a high attack success rate with more diverse, fluent and natural adversarial examples. In addition, our robustness enhancement method can significantly improve the robustness of models to resist adversarial attacks. Our work indicates that prompting paradigm has great potential in probing some fundamental flaws of PLMs and fine-tuning them for downstream tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

引用

International Conference on parallel and distributed Systems (ICPADS)

作者： Saiqin Long Zhetao Li Zihao Liu Qingyong Deng Sangyoon Oh Nobuyoshi Komuro Key Laboratory of Hunan Province for Internet of Things and Information Security Hunan International Scientific and Technological Cooperation Base of Intelligent network School of Computer Science Xiangtan University Xiangtan China Science and Technology on Parallel and Distributed Processing Laboratory (PDL) National University of Defense Technology Changsha China Ajou University Suwon South Korea Graduate School of Advanced Integration Science Chiba University Chiba Japan

ISBN: (数字)9781728190747

ISBN: (纸本)9781728183824

Deduplication is a data redundancy elimination technique, designed to save system storage resources by reducing redundant data in cloud storage systems. With the development of cloud computing technology, deduplication has been increasingly applied to cloud data centers. However, traditional technologies face great challenges in big data deduplication to properly weigh the two conflicting goals of deduplication throughput and high duplicate elimination ratio. This paper proposes a similarity clustering-based deduplication strategy (named SCDS), which aims to delete more duplicate data without significantly increasing system overhead. The main idea of SCDS is to narrow the query range of fingerprint index by data partitioning and similarity clustering algorithms. In the data preprocessing stage, SCDS uses data partitioning algorithm to classify similar data together. In the data deletion stage, the similarity clustering algorithm is used to divide the similar data fingerprint superblock into the same cluster. Repetitive fingerprints are detected in the same cluster to speed up the retrieval of duplicate fingerprints. Experiments show that the deduplication ratio of SCDS is better than some existing similarity deduplication algorithms, but the overhead is only slightly higher than some high throughput but low deduplication ratio methods.

关键词： Cloud computing Clustering algorithms Estimation Fingerprint recognition Throughput Partitioning algorithms Classification algorithms

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：