检索结果-内蒙古大学图书馆

2016 IEEE 13th International Conference on Signal Processing（ICSP2016）

作者： Weijiang Feng Naiyang Guan Zhigang Luo Institute of Software College of Computer National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology

Audio matching automatically retrieves all excerpts that have the same content as the query audio clip from given audio recordings. The extracted feature is critical for audio matching and the Chroma Energy Normalized Statistics(CENS) feature is the state-of-the-arts. However, CENS might behave unsatisfactorily on some audio because it is a handcraft feature. In this paper, we propose to utilize the features learned by Convolutional Deep Belief Network(CDBN) to enhance the performance of audio matching. Benefit from the strong generalization ability of CDBN, our method works better than CENS based methods on most audio datasets. Since the features learned by CDBN are binary-valued, we can develop a more efficient audio matching algorithm by taking the advantage of this property. Experimental results on both TIMIT dataset and a simulated music dataset confirm effectiveness of the proposed CDBN based method comparing with the traditional CENS feature based algorithm.

关键词： audio matching convolutional deep belief network content-based audio retrieval

来源：评论

学校读者我要写书评

暂无评论

Hard Contrastive Learning for Video Captioning

Hard Contrastive Learning for Video Captioning

引用

IEEE International Conference on Electronics and Communication Engineering (ICECE)

作者： Lilei Wu Jie Liu Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha China

ISBN: (纸本)9781665487900

Maximum likelihood estimation has been widely adopted along with the encoder-decoder framework for video captioning. However, it ignores the structure of sentences and restrains the diversity and distinction of generated captions. To address this issue, we propose a hard contrastive learning (HCL) method for video captioning. Specifically, built on the encoder-decoder framework, we introduce mismatched pairs to learn a reference distribution of video descriptions. The target model on the matched pairs is learned on top the reference model, which improves the distinctiveness of generated captions. In addition, we further boost the distinctiveness of the captions by developing a hard mining technique to select the hardest mismatched pairs within the contrastive learning framework. Finally, the relationships among multiple relevant captions for each video is consider to encourage the diversity of generated captions. The proposed method generates high quality captions which effectively capture the specialties in individual videos. Extensive experiments on two benchmark datasets, i.e., MSVD and MSR-VTT, show that our approach outperforms state-of-the-art methods.

关键词： Maximum likelihood estimation Visualization Video description Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Data Avenue: Remote Storage Resource Management in WS-PGRADE/gUSE

Data Avenue: Remote Storage Resource Management in WS-PGRADE...

引用

International Workshop on Science Gateways (IWSG)

作者： Ákos Hajnal Zoltán Farkas Péter Kacsuk Laboratory of Parallel and Distributed Systems Hungarian Academy of Sciences Budapest Hungary Computer Science and Software Engineering Department University of Westminster London United Kingdom

State-of-the-art gateways are connected to several distributed computing infrastructures (DCIs) and are able to run jobs and workflows simultaneously in all those different DCIs. However, the flexibility of accessing data storages belonging to different DCIs is a missing feature of current gateways. SZTAKI (Institute for Computer Science and Control) has developed a Data Avenue Blacktop service and aLiferay-based Data Avenue port let that open the door for integrating such features into science gateways. The paper explains the design considerations of the Data Avenue Blacktop service and its usage scenarios in science gateways through the Data Avenue port let.

关键词： Conferences Logic gates

来源：评论

学校读者我要写书评

暂无评论

Continuations for parallel logic programming 00

Continuations for parallel logic programming

引用

Proceedings of the 2nd International ACM SIGPLAN Conference on Principles and Practice of Declarative Programming (PPDP'00)

作者： Todoran, Eneia Papaspyrou, Nikolaos S. Technical University of Cluj-Napoca Dept. of Computer Science Parallel/Distributed Syst. Lab. Baritiu Str. 28 3400 Cluj-Napoca Romania Natl. Technical University of Athens Dept. of Elec./Computer Engineering Software Engineering Laboratory 15780 Zografou Greece

ISBN: (纸本)1581132654

This paper gives denotational models for three logic programming languages of progressive complexity, adopting the "logic programming without logic" approach. The first language is the control flow kernel of sequential Prolog, featuring sequential composition and backtracking. A committed-choice concurrent logic language with parallel composition (parallel AND) and don't care nondeterminism is studied next. The third language is the core of Warren's basic Andorra model, combining parallel composition and don't care nondeterminism with two forms of don't know nondeterminism (interpreted as sequential and parallel OR) and favoring deterministic over nondeterministic computation. We show that continuations are a valuable tool in the analysis and design of semantic models for both sequential and parallel logic programming. Instead of using mathematical notation, we use the functional programming language Haskell as a metalanguage for our denotational semantics, and employ monads in order to facilitate the transition from one language under study to another.

关键词： Logic programming

来源：评论

学校读者我要写书评

暂无评论

ST-PINN: A Self-Training Physics-Informed Neural Network for Partial Differential Equations

ST-PINN: A Self-Training Physics-Informed Neural Network for...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Junjun Yan Xinhai Chen Zhichao Wang Enqiang Zhoui Jie Liu Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha China Laboratory of Digitizing Software for Frontier Equipment National University of Defense Technology Changsha China

Partial differential equations (PDEs) are an essential computational kernel in physics and engineering. With the advance of deep learning, physics-informed neural networks (PINNs), as a mesh-free method, have shown great potential for fast PDE solving in various applications. To address the issue of low accuracy and convergence problems of existing PINNs, we propose a self-training physics-informed neural network, ST-PINN. Specifically, ST-PINN introduces a pseudo label based self-learning algorithm during training. It employs governing equation as the pseudo-labeled evaluation index and selects the highest confidence examples from the sample points to attach the pseudo labels. To our best knowledge, we are the first to incorporate a self-training mechanism into physics-informed learning. We conduct experiments on five PDE problems in different fields and scenarios. The results demonstrate that the proposed method allows the network to learn more physical information and benefit convergence. The ST-PINN outperforms existing physics-informed neural network methods and improves the accuracy by a factor of 1.33x-2.54x.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ProMoE: Fast MoE-based LLM Serving using Proactive Caching

arXiv

引用

arXiv 2024年

作者： Song, Xiaoniu Zhong, Zihang Chen, Rong Chen, Haibo Institute of Parallel and Distributed Systems Shanghai Jiao Tong University China Key Laboratory of System Software Chinese Academy of Sciences China Zhejiang University China

The promising applications of large language models are often limited by the constrained GPU memory capacity available on edge devices. Mixture-of-Experts (MoE) models help address this issue by activating only a subset of the model’s parameters during computation. This approach allows the unused parameters to be offloaded to host memory, thereby reducing the overall GPU memory demand. However, existing cache-based offloading solutions handle cache misses reactively, which significantly impacts system performance. In this paper, we introduce ProMoE, a novel proactive caching system that utilizes intermediate results to predict subsequent expert usage. By proactively fetching experts in advance, ProMoE eliminates passive cache misses, removes loading time from the critical path, and reduces the performance overhead associated with offloading. Our evaluations demonstrate that ProMoE achieves an average speedup of 2.20× (up to 3.21×) and 2.07× (up to 5.02×) in the prefill and decode stages, respectively, compared to existing offloading solutions. © 2024, CC BY.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Optimizing All-to-All Collective Communication on Tianhe Supercomputer

Optimizing All-to-All Collective Communication on Tianhe Sup...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Jintao Peng Jie Liu Yi Dai Min Xie Chunye Gong National University of Defense Technology ChangSha China Science and Technology on Parallel and Distributed Processing Laboratory NUDT Changsha China Changsha and Laboratory of Software Engineering for Complex System NUDT Changsha China

All-to-all communication has a wide range of ap-plications in parallel applications like FFT. On most supercom-puters, there are multiple cores in a node. Message aggregation is an efficient method for smaller messages. Using multi-leader to aggregate message show significant improvement in intra-node overhead. However, compared to one-leader aggregation, existing multi-leader design incurs more message count and less aggregated message size. This paper proposes an Overlapped Multi-worker Multi-port all-to-all (OVALL) to scale the message size and parallelism of the aggregation algorithm. The algorithm exploits the all-to-all multi-core parallelism, concurrent commu-nication, and overlapping capabilities. Experiment results show that, compared to systems built-in MPI, OVALL'implementation achieves up to 5.9x or 18x speedup compared to MPI on different HPC systems. For the Fast Fourier Transform (FFT) application, OVALL is up to 2.7x (8192 cores, system A) or 5.6x (4800 cores, system B) faster compared to built-in MPI on peak performance.

关键词： Multicore processing Fast Fourier transforms Scalability Aggregates Supercomputers Libraries Pipeline processing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Code Representation Learning for Code Search with Abstract Code Semantics

Enhancing Code Representation Learning for Code Search with ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Shaojie Zhang Yiwei Ding Enrui Hu Yue Yu Yu Zhang Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Peng Cheng Laboratory Shenzhen China Distributed and Parallel Software Lab Huawei Shenzhen China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Code representation learning is an important way to encode the semantics of source code through pre-training. The learned representation supports a variety of downstream tasks, such as natural language code search and code defect detection. Inspired by pre-trained models for natural language representation learning, existing approaches often treat the source code or its structural information (e.g., Abstract Syntax Tree or AST) as a plain token sequence. Unlike natural language, programming language has its unique code unit information (e.g., identifiers and expressions) and logic information (e.g., the functionality of a code snippet). To further explore those properties, we propose Abstract Code Embedding (AbCE), a self-supervised learning method that considers the abstract semantics of code logic. Instead of scattered tokens, AbCE treats an entire node or a subtree in an AST as a basic code unit during pre-training, which preserves the entirety of a coding unit. Moreover, AbCE learns the abstract semantics of AST nodes via a self-distillation way. Experimental results show that it achieves significant improvements over state-of-the-art baselines on code search tasks and comparable performance on code clone detection and defect detection tasks even without using contrastive learning or curriculum learning.

关键词： Representation learning Codes Source coding Semantics Natural languages Cloning Syntactics

来源：评论

学校读者我要写书评

暂无评论

Semantic configuration management model using a path dependence flow graph

引用

Systems and Computers in Japan 1999年第5期30卷 47-55页

作者： Naoi, Kuniaki Takahashi, Naohisa NTT Software Laboratories Musashino 180 Japan NTT Optical Netwk. Syst. Labs. Musashino 180 Japan Waseda University Global Computing Laboratory NTT Software Laboratories Technical University Berlin Germany Info. Processing Society of Japan Japan Soc. Software Sci. Technol. ACM IEEE Computer Society University of Electro-Communications Tokyo Institute of Technology NTT Elec. Commun. Laboratories Parallel Distributed Arch.'s Res. G. NTT Optical Netwk. Syst. Labs. Info. Processing Society of Japan ACM

If a program is not executed as expected, we say that a semantic error has occurred in the program. As is well known, semantic errors sometimes appear in a program because the modification intention was not correctly reflected in the new configuration. In order to avoid as many semantic errors as possible, as well as to efficiently locate errors, the authors are developing a semantic configuration management (SCM) model that is capable of efficiently performing various analyses of programs in a unified framework. Previously, the following techniques have been proposed in the SCM model: an analysis technique for detecting infeasible paths (IFPs) from the program, and an analysis technique for generating various kinds of slices in a unified framework. This paper proposes a technique for accurately computing program slices using the IFPs in the SCM model. Next, it proposes a technique for improving the accuracy of detecting semantic errors during merging of several modifications by using accurate program slices. In addition, new applications are proposed for the various slices.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Feature and Performance Comparison of FaaS Platforms 14

Feature and Performance Comparison of FaaS Platforms

引用

14th IEEE International Conference on software Engineering and Service Science, ICSESS 2023

作者： Ma, Penghui Shi, Peichang Yi, Guodong College of Computer Science National University of Defense Technology National Key Laboratory of Parallel and Distributed Processing Changsha410073 China College of Computer Science National University of Defense Technology Key Laboratory of Software Engineering for Complex Systems Changsha410073 China Xiangjiang Lab Changsha410073 China School of Advanced Interdisciplinary Studies Hunan University of Technology and Business Changsha410073 China

ISBN: (纸本)9798350336269

With serverless computing offering more efficient and cost-effective application deployment, the diversity of serverless platforms presents challenges to users, including platform lock-in and costly migration. Moreover, due to the black box nature of function computing, traditional performance benchmarking methods are not applicable, necessitating new studies. This article presents a detailed comparison of six major public cloud function computing platforms and introduces a benchmarking framework for function computing performance. This framework aims to help users make comprehensive comparisons and select the most suitable platform for their specific needs. © 2023 IEEE.

关键词： Benchmarking

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：