检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

123 篇 会议
65 篇 期刊文献

馆藏范围

188 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

128 篇 工学
- 105 篇 计算机科学与技术...
- 84 篇 软件工程
- 24 篇 信息与通信工程
- 22 篇 生物工程
- 19 篇 控制科学与工程
- 16 篇 电子科学与技术（可...
- 9 篇 电气工程
- 8 篇 机械工程
- 5 篇 化学工程与技术
- 4 篇 动力工程及工程热...
- 4 篇 土木工程
- 3 篇 力学（可授工学、理...
- 3 篇 仪器科学与技术
- 3 篇 材料科学与工程（可...
- 3 篇 建筑学
- 3 篇 航空宇航科学与技...
- 3 篇 农业工程
- 3 篇 安全科学与工程
- 3 篇 网络空间安全
51 篇 理学
- 26 篇 数学
- 23 篇 生物学
- 8 篇 物理学
- 6 篇 化学
- 6 篇 统计学（可授理学、...
- 4 篇 系统科学
41 篇 管理学
- 27 篇 管理科学与工程(可...
- 15 篇 图书情报与档案管...
- 9 篇 工商管理
6 篇 经济学
- 6 篇 应用经济学
3 篇 法学
3 篇 教育学
- 3 篇 教育学
3 篇 农学
2 篇 医学

主题

9 篇 computational mo...
9 篇 training
7 篇 deep neural netw...
7 篇 feature extracti...
7 篇 data models
6 篇 performance eval...
5 篇 task analysis
5 篇 anomaly detectio...
4 篇 self-supervised ...
4 篇 graph neural net...
4 篇 predictive model...
4 篇 semantics
4 篇 machine learning
4 篇 kernel
4 篇 graphics process...
4 篇 accuracy
4 篇 cryptography
3 篇 deep learning
3 篇 computer archite...
3 篇 neural networks

机构

36 篇 college of compu...
14 篇 national key lab...
10 篇 national key lab...
10 篇 national key lab...
10 篇 national key lab...
8 篇 national key lab...
8 篇 national key lab...
7 篇 xiangjiang lab
6 篇 college of compu...
6 篇 science and tech...
5 篇 key laboratory o...
5 篇 school of advanc...
5 篇 national key lab...
4 篇 school of automa...
4 篇 national univers...
4 篇 national key lab...
4 篇 college of compu...
4 篇 sino-german coll...
4 篇 college of syste...
4 篇 nuclear power in...

作者

13 篇 li dongsheng
13 篇 wang yijie
12 篇 wang huaimin
11 篇 huaimin wang
10 篇 lai zhiquan
8 篇 dongsheng li
8 篇 ding bo
7 篇 peichang shi
7 篇 xu hongzuo
7 篇 xu kele
6 篇 dou yong
6 篇 yijie wang
6 篇 wang wei
6 篇 zhiquan lai
6 篇 qiao peng
6 篇 wang xiaodong
6 篇 yue yu
5 篇 guodong yi
5 篇 wang tao
5 篇 jinshu su

语言

176 篇 英文
7 篇 中文
5 篇 其他

检索条件"机构=National Key Laboratory of Parallel and Distributed Computing College of Computer"

共 188 条记录，以下是81-90 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Local-Adaptive Transformer for Multivariate Time Series Anomaly Detection and Diagnosis

Local-Adaptive Transformer for Multivariate Time Series Anom...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Xiaohui Zhou Yijie Wang Hongzuo Xu Mingyu Liu Ruyi Zhang National Key Laboratory of Parallel and Distributed Computing College of Computer National University of Defense Technology Changsha China

Time series data are pervasive in varied real-world applications, and accurately identifying anomalies in time series is of great importance. Many current methods are insufficient to model long-term dependence, whereas some anomalies can be only identified through long temporal contextual information. This may finally lead to disastrous outcomes due to false negatives of these anomalies. Prior arts employ Transformers (i.e., a neural network architecture that has powerful capability in modeling long-term dependence and global association) to alleviate this problem; however, Transformers are insensitive in sensing local context, which may neglect subtle anomalies. Therefore, in this paper, we propose a local-adaptive Transformer based on cross-correlation for time series anomaly detection, which unifies both global and local information to capture comprehensive time series patterns. Specifically, we devise a cross-correlation mechanism by employing causal convolution to adaptively capture local pattern variation, offering diverse local information into the long-term temporal learning process. Furthermore, a novel optimization objective is utilized to jointly optimize reconstruction of the entire time series and matrix derived from cross-correlation mechanism, which prevents the cross-correlation from becoming trivial in the training phase. The generated cross-correlation matrix reveals underlying interactions between dimensions of multivariate time series, which provides valuable insights into anomaly diagnosis. Extensive experiments on six real-world datasets demonstrate that our model outperforms state-of-the-art competing methods and achieves 6.8%-27.5% $F_{1}$ score improvement. Our method also has good anomaly interpretability and is effective for anomaly diagnosis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rethinking the distributed DNN Training Cluster Design from the Cost-effectiveness View

Rethinking the Distributed DNN Training Cluster Design from ...

引用

IEEE International Conference on High Performance computing and Communications (HPCC)

作者： Zhiquan Lai Yujie Liu Wei Wang Yanqi Hao Dongsheng Li National Key Laboratory of Parallel and Distributed Computing College of Computer National University of Defense Technology Changsha China

As deep learning grows rapidly, model training heavily relies on parallel methods and there exist numerous cluster configurations. However, current preferences for parallel training focus on data centers, overlooking the financial constraints faced by most researchers. To attain the best performance within the cost limitation, we introduce a throughput-cost metric to accurately characterize clusters' cost-effectiveness. Based on this metric, we design a cost-effective cluster featuring the 3090 with NVLink. The experiment results demonstrate that our cluster achieves remarkable cost-effectiveness in various distributed model training schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Communication Analysis for Multidimensional parallel Training of Large-scale DNN Models

Communication Analysis for Multidimensional Parallel Trainin...

引用

IEEE International Conference on High Performance computing and Communications (HPCC)

作者： Zhiquan Lai Yanqi Hao Shengwei Li Dongsheng Li National Key Laboratory of Parallel and Distributed Computing College of Computer National University of Defense Technology Changsha China

Multidimensional parallel training has been widely applied to train large-scale deep learning models like GPT-3. The efficiency of parameter communication among training devices/processes is often the performance bottleneck of large model training. Analysis of parameter communication mode and traffic has important reference significance for the research of interconnection network design and computing task scheduling to improve the training performance. In this paper, we analyze the parametric communication modes in typical 3D parallel training (data parallelism, pipeline parallelism, and tensor parallelism), and model the traffic in different communication modes. Finally, taking GPT-3 as an example, we present the communication in its 3D parallel training.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Integrated Detection of SQL Injection Behavior Based on Text Features and Traffic Features 10th

Research on Integrated Detection of SQL Injection Behavior B...

引用

10th International Conference on computer Engineering and Networks, CENet 2020

作者： Li, Ming Liu, Bo Xing, Guangsheng Wang, Xiaodong Wang, Zhihui College of Intelligence Science and Technology National University of Defence Technology Changsha410073 China National Key Laboratory of Parallel and Distributed Processing College of Computer Science and Technology National University of Defence Technology Changsha410073 China

ISBN: (纸本)9789811584619

With the rapid development of Internet technology, various network attack methods come out one after the other. SQL injection has become one of the most severe threats to Web applications and seriously threatens various Web application services and users data security. There are both traditional detection methods and emerging methods based on deep learning technology with higher detection accuracy for the detection of SQL injection. However, they are all for detecting a single statement and cannot determine the stage of the attack. To further improve the effect of SQL injection detection, this paper proposes an integrated detection framework for SQL injection behavior based on both text features and traffic features. We propose a SQL-LSTM model based on deep learning technology as the detection model at the text features level. Meanwhile, the features of the data traffic are merged. By this integrated method, the detection effect of SQL injection is further improved. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Efficient Large Models Fine-tuning on Commodity Servers via Memory-balanced Pipeline parallelism

Efficient Large Models Fine-tuning on Commodity Servers via ...

引用

IEEE International Conference on High Performance computing and Communications (HPCC)

作者： Yujie Liu Zhiquan Lai Weijie Liu Wei Wang Dongsheng Li National Key Laboratory of Parallel and Distributed Computing College of Computer National University of Defense Technology Changsha China

Large models have achieved impressive performance in many downstream tasks. Using pipeline parallelism to fine-tune large models on commodity GPU servers is an important way to make the excellent performance of large models available to the general public. Previous solutions fail to achieve an efficient memory-balanced pipeline parallelism. In this poster, we introduce a memory load-balanced pipeline parallel solution. This solution balances memory consumption across stages on commodity GPU servers via NVLink bridges. It establishes a new pathway to offload data from GPU to CPU by using the PCIe link of adjacent GPUs connected by the NVLink bridge. Furthermore, our method orchestrates offload operations to minimize the offload latency during large model fine-tuning. Experiments demonstrate that our solution can balance the memory footprint among pipeline stages without sacrificing training performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boundary-Driven Active Learning for Anomaly Detection in Time Series Data Streams

Boundary-Driven Active Learning for Anomaly Detection in Tim...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiaohui Zhou Yijie Wang Hongzuo Xu Mingyu Liu National Key Laboratory of Parallel and Distributed Computing College of Computer National University of Defense Technology Changsha China

The key to anomaly detection in time series data streams (TSDS) lies in the ability to adapt to evolving data. Active learning for anomaly detection has shown such ability by leveraging expert feedback. However, many studies in this research line strive to optimize performance by exhausting the query budget, lacking consideration of query necessity, which means some unnecessary queries may wrongly lead the model to overfit the trivial information and incur additional consumption in both human labeling and model execution. This paper proposes Boundary-driven Active Learning for Anomaly Detection (BALAD). BALAD utilizes deep one-class classification to construct a hypersphere boundary to sense data abnormality and filters out unnecessary queries by dividing the boundary region. We further harness the hypersphere boundary to quantitatively measure data difficulty, and a focal loss is introduced to prioritize hard samples. The boundary is flexibly adapted during each feedback iteration to accommodate changes in TSDS. Extensive experiments on six datasets demonstrate that BALAD significantly outperforms the state-of-the-art anomaly detection methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DrugProtKGE: Weakly Supervised Knowledge Graph Embedding for Highly-Effective Drug-Protein Interaction Representation

DrugProtKGE: Weakly Supervised Knowledge Graph Embedding for...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Qiu, Yanlong Wang, Siqi Yang, Xi Qiu, Xinyuan Wu, Chengkun Cui, Yingbo Yang, Canqun National University of Defense Technology Institute for Quantum Information State Key Laboratory of High-Performance Computing College of Computer Science Hunan Changsha410073 China National Supercomputer Center in Tianjin Tianjin300457 China National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing College of Computer Science Hunan Changsha410073 China National University of Defense Technology Department of Biology and Chemistry College of Science Hunan Changsha410073 China

ISBN: (纸本)9798350337488

With the exponential growth of biomedical knowledge in unstructured text repositories such as PubMed, it is imminent to establish a knowledge graph-style, efficient searchable and targeted database that can support the need of information retrieval from researchers and clinicians. To mine knowledge from graph databases, most previous methods view a triple in a graph (see Fig. 1) as the basic processing unit and embed the triplet element (i.e. drugs/chemicals, proteins/genes and their interaction) as separated embedding matrices, which cannot capture the semantic correlation among triple elements. To remedy the loss of semantic correlation caused by disjoint embeddings, we propose a novel approach to learn triple embeddings by combining entities and interactions into a unified representation. Furthermore, traditional methods usually learn triple embeddings from scratch, which cannot take advantage of the rich domain knowledge embedded in pre-trained models, and is also another significant reason for the fact that they cannot distinguish the differences implied by the same entity in the multi-interaction triples. In this paper, we propose a novel fine-tuning based approach to learn better triple embeddings by creating weakly supervised signals from pre-trained knowledge graph embeddings. The method automatically samples triples from knowledge graphs and estimates their pairwise similarity from pre-trained embedding models. The triples are then fed pairwise into a Siamese-like neural architecture, where the triple representation is fine-tuned in the manner bootstrapped by triple similarity scores. Finally, we demonstrate that triple embeddings learned with our method can be readily applied to several downstream applications (e.g. triple classification and triple clustering). We evaluated the proposed method on two open-source drug-protein knowledge graphs constructed from PubMed abstracts, as provided by BioCreative. Our method achieves consistent improvement in both t

关键词： Drug-Protein Interaction Knowledge Graph Embedding Triple Embedding Weakly Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

HSDP: Accelerating Large-scale Model Training via Efficient Sharded Data parallelism

HSDP: Accelerating Large-scale Model Training via Efficient ...

引用

International Symposium on parallel and distributed Processing with Applications, ISPA

作者： Yanqi Hao Zhiquan Lai Wei Wang Shengwei Li Weijie Liu Keshi Ge Dongsheng Li National Key Laboratory of Parallel and Distributed Computing(PDL) College of Computer National University of Defense Technology Changsha China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Large deep neural network (DNN) models have demonstrated exceptional performance across diverse downstream tasks. Sharded data parallelism (SDP) has been widely used to reduce the memory footprint of model states. In a DNN training cluster, a device usually has multiple inter-device links that connect to other devices, like NVLink and InfiniBand. However, existing SDP approaches employ a single link at any given time, encountering challenges in efficient training due to significant communication overheads. We observe that the inter-device links can work independently without affecting each other. To reduce the fatal communication overhead of distributed training of large DNNs, this paper introduces HSDP, an efficient SDP training approach that enables the simultaneous utilization of multiple inter-device links. HSDP partitions models in a novel fine-grained manner and orchestrates the communication processes of partitioned parameters while considering inter-device links. This design enables concurrent communication execution and reduces communication overhead. To further optimize the training performance of HSDP, we propose a HSDP planner. The HSDP planner first abstracts the model partition and execution of HSDP into a communication parallel strategy, and builds a cost model to estimate the performance of each strategy. We then formulate the strategy searching as an optimization problem and solve it with an off-the-shelf solver. Evaluations on representative DNN workloads demonstrate that HSDP achieves up to 1.30× speedup compared to the state-of-the-art SDP training approaches.

关键词： Training Performance evaluation Costs distributed databases Artificial neural networks parallel processing Throughput Search problems Data models Optimization

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

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

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共19页 << < 5 6 7 8 9 10 11 12 13 14 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：