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

5,634 篇 会议
90 篇 期刊文献
10 册 图书

馆藏范围

5,734 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,774 篇 工学
- 2,332 篇 计算机科学与技术...
- 1,329 篇 软件工程
- 567 篇 信息与通信工程
- 466 篇 电气工程
- 200 篇 生物工程
- 174 篇 控制科学与工程
- 174 篇 生物医学工程（可授...
- 109 篇 机械工程
- 84 篇 交通运输工程
- 83 篇 化学工程与技术
- 80 篇 电子科学与技术（可...
- 79 篇 光学工程
- 69 篇 仪器科学与技术
- 65 篇 动力工程及工程热...
- 55 篇 土木工程
- 55 篇 安全科学与工程
897 篇 理学
- 478 篇 数学
- 235 篇 生物学
- 231 篇 物理学
- 191 篇 统计学（可授理学、...
- 119 篇 系统科学
- 66 篇 化学
589 篇 管理学
- 327 篇 图书情报与档案管...
- 305 篇 管理科学与工程(可...
- 163 篇 工商管理
289 篇 医学
- 243 篇 临床医学
- 144 篇 基础医学(可授医学...
- 80 篇 药学(可授医学、理...
- 52 篇 公共卫生与预防医...
76 篇 法学
- 71 篇 社会学
54 篇 经济学
45 篇 教育学
39 篇 农学
26 篇 文学
2 篇 军事学
1 篇 历史学
1 篇 艺术学

主题

1,600 篇 data models
535 篇 predictive model...
530 篇 training
498 篇 machine learning
461 篇 data mining
416 篇 big data
405 篇 computational mo...
343 篇 feature extracti...
333 篇 task analysis
327 篇 prediction algor...
268 篇 deep learning
255 篇 machine learning...
245 篇 classification a...
238 篇 analytical model...
191 篇 clustering algor...
190 篇 support vector m...
183 篇 neural networks
158 篇 natural language...
142 篇 training data
141 篇 mathematical mod...

机构

19 篇 sun yat sen univ...
19 篇 daffodil interna...
12 篇 univ chinese aca...
11 篇 tsinghua univers...
11 篇 university of ch...
11 篇 school of data a...
10 篇 carnegie mellon ...
9 篇 renmin univ chin...
9 篇 lviv polytechnic...
8 篇 shenzhen researc...
7 篇 shanghai jiao to...
7 篇 college of compu...
7 篇 university of el...
7 篇 school of comput...
7 篇 national univers...
7 篇 harbin institute...
7 篇 beijing key lab ...
7 篇 natl univ def te...
7 篇 renmin univ chin...
6 篇 university of sc...

作者

7 篇 li li
7 篇 wang wei
7 篇 xiao yanghua
6 篇 wen ji-rong
6 篇 cui bin
6 篇 zhao wayne xin
6 篇 ying liu
6 篇 syed akhter hoss...
5 篇 yang tong
5 篇 liu yang
5 篇 li zhang
5 篇 jia weijia
5 篇 chen liu
5 篇 yang yang
5 篇 xiao hongbo
5 篇 nguyen trong-the
5 篇 yu jie
5 篇 albert bifet
5 篇 wang bin
5 篇 carlos ordonez

语言

5,596 篇 英文
130 篇 其他
14 篇 中文
2 篇 俄文
1 篇 乌克兰文

检索条件"任意字段=2020 International Conference on Data Processing Algorithms and Models, ICDPAM 2020"

共 5734 条记录，以下是771-780 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：

Research on the Application of Semantic Role Labeling Based on Graph Convolutional Networks in Discourse Comprehension

Research on the Application of Semantic Role Labeling Based ...

引用

Computers, Information processing and Advanced Education (CIPAE), 2020 international conference on

作者： Jian Zhang Xi'an Eurasia University Xi'an China

ISBN: (数字)9798331527662

ISBN: (纸本)9798331527679

This study aims to explore the application of graph convolutional networks in semantic role labeling tasks in order to improve the depth and breadth of discourse understanding. Traditional semantic role labeling methods tend to focus on the capture of sequence information, but ignore the complex dependency between words. In order to solve this problem, the graph convolutional network is introduced into the semantic role labeling task for the first time in this study, and the long-distance dependency between words is effectively captured by constructing sentence-level graph structures. GCN model can integrate local and global semantic information at the same time, to identify and label semantic roles more accurately. In order to verify the validity and generalization ability of the proposed model, detailed simulation experiments are carried out on several public benchmark datasets. The experimental results show that compared with the existing semantic role annotation methods based on sequence annotation or tree structure, the proposed GCN model has achieved significant improvement in F1 value. This achievement not only fully proves the great potential of graph convolutional networks in semantic role labeling tasks, but also provides a new perspective and method for the study of discourse understanding.

关键词： Accuracy Graph convolutional networks Annotations Semantics Education Information processing Benchmark testing Syntactics data models Labeling

来源：评论

学校读者我要写书评

暂无评论

Efficiently Answering Why-Not Questions on Radius-Bounded k-Core Searches 28th

Efficiently Answering Why-Not Questions on Radius-Bounded k...

引用

28th international conference on database Systems for Advanced Applications, DASFAA 2023

作者： Zong, Chuanyu Dong, Zefang Yang, Xiaochun Wang, Bin Qiu, Tao Zhu, Huaijie School of Computer Science Shenyang Aerospace University Liaoning110136 China School of Computer Science and Engineering Northeastern University Liaoning110819 China Laboratory of Big Data Analysis and Processing Sun Yat-sen University Guangdong510275 China

ISBN: (纸本)9783031306747

The problem of searching radius-bounded k-cores (RB-k-cores) for a given query vertex is to find cohesive subgraphs satisfying both social and spatial constraints on geo-social networks. However, the search results are effected by two parameters: the cohesive constraint k and the query radius r. Furthermore, as the users lack of enough professional knowledge, it is very hard to provide reasonable parameters for RB-k-core searches. In this case, some users will confuse that why some expected vertices are not included in the search results, which called why-not questions. Therefore, we will investigate the problem of answering why-not questions on radius-bound k-core searches in this paper, which is to find why some expected vertices are missing in the search results and how to make the expected vertices appear in the same RB-k-cores with query vertices. To tackle this problem, we firstly analyze the effect of the two parameters on the search results of RB-k-core searches. Then, we explore two effective algorithms by refining the initial search parameters k and r of RB-k-core searches. Finally, we conduct comprehensive experimental studies on four real geo-social networks to evaluate both the effectiveness and efficiency of our proposed explanation algorithms. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Regression and Regularization Methods: Application to Weather and Climate data 6th

Comparative Study of Regression and Regularization Methods:...

引用

6th international conference on Wireless Technologies, Embedded and Intelligent Systems, WITS 2020

作者： Raouhi, El Mehdi Lachgar, Mohamed Kartit, Ali LTI Laboratory ENSA University Chouaib Doukkali El Jadida Morocco

ISBN: (纸本)9789813368927

Regression analysis is a powerful statistical method that support to inspect the relationship between two or more variables of interest. While there are many types of regression analysis, at their core they all examine the impact of one or more independent variables on a dependent variable. It is one of the most commonly used methods in many scientific fields. Satisfying the assumptions such as collinearity between variables ought to be a significant issue in data science. Advanced level tools such as Linear, Lasso, Ridge and ElasticNet regression are methods designed to overcoming a problem of overfitting a model. This study discusses comparing regression and regularization algorithms. It also deals with how the concept of model complexity unfolds for each of these models and provides an overview of how each algorithm builds a model. Moreover, it examines the strengths and weaknesses of each algorithm, as well as the type of data to which they can best be applied to irrigation water use efficiency under climate change. Finally, this work aims also to explain the meaning of the most important regularization criteria. It remains to say that the main contributions of this study are (1) Comparing linear and multilinear regression methods: case of climate change dataset using regression metrics (2) comparing regularization methods: Ridge, Lasso and ElasticNet. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Irrigation

来源：评论

学校读者我要写书评

暂无评论

FedCav: Contribution-aware Model Aggregation on Distributed Heterogeneous data in Federated Learning 21

FedCav: Contribution-aware Model Aggregation on Distributed ...

引用

50th international conference on Parallel processing (ICPP)

作者： Zeng, Hui Zhou, Tongqing Guo, Yeting Cai, Zhiping Liu, Fang Natl Univ Def Technol Coll Comp Changsha Peoples R China Hunan Univ Sch Design Changsha Peoples R China

ISBN: (纸本)9781450390682

The emerging federated learning (FL) paradigm allows multiple distributed devices to cooperatively train models in parallel with the raw data retained locally. The local-computed parameters will be transferred to a centralized server for aggregation. However, the vanilla aggregation method ignores the heterogeneity of the distributed data, which may lead to slow convergence and low training efficiency. Yet, existing data scheduling and improved aggregation methods either incur privacy concerns or fail to consider the finegrained heterogeneity. We propose FedCav, a contribution-aware model aggregation algorithm that differentiates the merit of local updates and explicitly favors the model-informed contributions. The intuition is that the local data showing higher inference loss is likely to facilitate better performance improvement. To this end, we design a novel global loss function with explicit optimization preference on informative local updates, theoretically prove its convex property, and use it to regulate the gradient descent process iteratively. Additionally, we propose to identify abnormal updates with fake loss by auditing historic local training statistics. The results of extensive experiments demonstrate that FedCav needs fewer training rounds (similar to 34%) for convergence and achieves better inference accuracy (similar to 2.4%) than the baselines (i.e., FedAvg and FedProx). We also observe that FedCav can actively mitigate the model replacement attacks with agile recovery capability towards the aggregation.

关键词： federated learning data heterogeneity model replacement

来源：评论

学校读者我要写书评

暂无评论

Integrating IoT, Blockchain, and Vision Transformers for Enhanced Security and Efficiency in Smart Home and Healthcare Systems

Integrating IoT, Blockchain, and Vision Transformers for Enh...

引用

Computing and Information Technology (ICCIT-1441), 2020 international conference on

作者： Salman Jan Toqeer Ali Syed Saad Said Alqahtany Sohail Iqbal Ijaz Khan Shahrulniza Musa Faculty of Computer Studies Arab Open University A'Ali Kingdom of Bahrain Faculty of Computer and Information System Islamic University Madinah Madinah Saudi Arabia Department of Information Technology Alburaimi University College Alburaimi Oman Malaysian Institute of Information Technology Universiti Kuala Lumpur Kuala Lumpur Malaysia

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

Internet of Things (IoT) and cloud computing have revolutionized various realms including healthcare, education, industries and businesses. Wearable health monitors, smart medical equipment continuously collect patients data that are sent to cloud computing that possess powerful analytical tools facilitating individuals and healthcare units in terms of personalized treatment, proactive real-time health management, remote patient monitoring. For an efficient processing, edge computing satiated in terms of analysis however this decentralized nature, edge computing is significantly targeted and exposed to security threats and cyber attacks due to inhibition of vulnerabilities and breaches in the IoT devices. This research study focuses on enhancing strengths of edge computing to insure the reliability and integrity of data by utilizing the Blockchain infrastructure. This research also utilizes the transformer models to identify the real and fake data that fosters trust in edge computing technologies.

关键词： Computer vision Computational modeling data security Medical services Smart homes Transformers Threat assessment Blockchains Internet of Things Edge computing

来源：评论

学校读者我要写书评

暂无评论

Noise Stability Regularization for Improving BERT Fine-tuning

Noise Stability Regularization for Improving BERT Fine-tunin...

引用

conference of the North-American-Chapter of the Association-for-Computational-Linguistics - Human Language Technologies (NAACL-HLT)

作者： Hua, Hang Li, Xingjian Dou, Dejing Xu, Chengzhong Luo, Jiebo Univ Rochester Rochester NY 14627 USA Baidu Res Big Data Lab Beijing Peoples R China Univ Macau Dept Comp Sci Macau Peoples R China Baidu Res Beijing Peoples R China

ISBN: (纸本)9781954085466

Fine-tuning pre-trained language models such as BERT has become a common practice dominating leaderboards across various NLP tasks. Despite its recent success and wide adoption, this process is unstable when there are only a small number of training samples available. The brittleness of this process is often reflected by the sensitivity to random seeds. In this paper, we propose to tackle this problem based on the noise stability property of deep nets, which is investigated in recent literature (Arora et al., 2018;Sanyal et al., 2020). Specifically, we introduce a novel and effective regularization method to improve fine-tuning on NLP tasks, referred to as Layer-wise Noise Stability Regularization (LNSR). We extend the theories about adding noise to the input and prove that our method gives a stabler regularization effect. We provide supportive evidence by experimentally confirming that well-performing models show a low sensitivity to noise and fine-tuning with LNSR exhibits clearly higher generalizability and stability. Furthermore, our method also demonstrates advantages over other state-of-the-art algorithms including L-2-SP (Li et al., 2018), Mixout (Lee et al., 2020) and SMART (Jiang et al., 2020).

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

international conference "Marchuk Scientific Readings 2020", MSR 2020, Dedicated to the 95th Anniversary of the Birthday of RAS Academician Guri. I. Marchuk

International Conference "Marchuk Scientific Readings 2020",...

引用

international conference on Marchuk Scientific Readings 2020, MSR 2020

The proceedings contain 73 papers. The topics discussed include: numerical modeling of non-stationary heat problems in a two-phase medium;nested alternating - triangular incomplete factorization methods;two-level iterative methods for solving the saddle point problems;zero and first-degree spline multiwavelets and parallel computing;a computer system for the leukocytes classification in medical images;sign language recognition through leap motion controller and input prediction algorithm;a modified algorithm of the latent semantic analysis for text processing in the Russian language;evolutionary synthesis of nonlinear models based on metaheuristic programming and templates;some properties of the classification algorithms using ensemble kernels;the development of a system for automated ontology building based on heterogeneous ontology design patterns;and numerical research of the influence of wall heating on the turbulent flow pattern in an idealized street canyon.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Short-term Traffic Flow Prediction by Graph Deep Learning with Spatial Temporal Modeling 2

Short-term Traffic Flow Prediction by Graph Deep Learning wi...

引用

2nd international conference on Electronic Information Technology and Smart Agriculture, ICEITSA 2022

作者： Yuan, Lilian Fang, Weilin Xiao, Hongbo Xiao, Jianhua Shi, Yuanquan Yang, Yujun School of Computer Science and Engineering Huaihua University Hunan Huaihua418000 China Intelligent Processing and Application in Hunan Province Universities Key Laboratory of Wuling-Mountain Health Big Data Hunan Huaihua418000 China Wuling-Mountain Ecological Agriculture in Hunan Province Key Laboratory of Intelligent Control Technology for Huaihua Hunan418000 China

ISBN: (纸本)9781665464017

An extensive amount of research applications on traffic flow prediction models taking into account spatio-temporal modeling have been undertaken in recent years. Relative to traditional spatio-temporal modeling approaches, good application results have been achieved in predicting traffic flow. However, in real life, traffic flow proves to be time- and space-dependent, which poses difficulties for accurate modeling of traffic flow prediction. To address these problems, we propose the ST-GNN-GRU model, which mainly contains S-GNN and T-GRU modules. The model uses a combination of spatio-temporal modeling and deep learning, which can not only cope with the spatio-temporal modeling problem, but also improve the traffic flow prediction accuracy. The experiments are conducted using the METR-LA dataset, and the outcomes show that the proposed method performs more effectively than other baseline approaches. © 2022 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

7th Latin American High Performance Computing conference, CARLA 2020

7th Latin American High Performance Computing Conference, CA...

引用

7th Latin American High Performance Computing conference, CARLA 2020

ISBN: (纸本)9783030680343

The proceedings contain 15 papers. The special focus in this conference is on Latin American High Performance Computing. The topics include: Electricity Demand Forecasting Using Computational Intelligence and High Performance Computing;Parallel/Distributed Generative Adversarial Neural Networks for data Augmentation of COVID-19 Training Images;analysis of Regularization in Deep Learning models on Testbed Architectures;computer Application for the Detection of Skin Diseases in Photographic Images Using Convolutional Neural Networks;Neocortex and Bridges-2: A High Performance AI+HPC Ecosystem for Science, Discovery, and Societal Good;Fostering Remote Visualization: Experiences in Two Different HPC Sites;high Performance Computing Simulations of Granular Media in Silos;performance Analysis of Main Public Cloud Big data Services processing Brazilian Government data;accelerating Machine Learning algorithms with TensorFlow Using Thread Mapping Policies;Methodology for Design and Implementation an Efficient HPC Cluster;estimating the Execution Time of the Coupled Stage in Multiscale Numerical Simulations;Using HPC as a Competitive Advantage in an international Robotics Challenge;a Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain and Artificial Intelligence in Real Estate 8th

Blockchain and Artificial Intelligence in Real Estate

引用

8th international conference on Decision Support System Technology, ICDSST 2022

作者： Ziakis, Christos Department of Economic Sciences International Hellenic University Serres62124 Greece

ISBN: (纸本)9783031065293

Since their development, blockchain and artificial intelligence (AI) technologies have gained substantial momentum and immense adoption in different industries worldwide. The innovations of cryptocurrencies and machine learning algorithms have had significant implications for the growth and advancement of these technologies. The combination of the two presents incredible benefits to organizations in various sectors in terms of harnessing existing data for pattern recognition and insight identification. The technologies have impacted how industries do their businesses. This study includes a systematic review that explores how blockchain and AI, have changed the real estate industry, as well as the way the related businesses can take advantage of the technologies’ capabilities to stay afloat within this new technological development. This research adopts the Prisma methodology to explore how the application of blockchain and AI has impacted the real estate sector. The main finding is that in real estate, the combination of blockchain and AI has great potential, especially in modeling data and valuation, storing information in digital formats and securing transactions. © 2022, Springer Nature Switzerland AG.

关键词： Blockchain

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500页 << < 74 75 76 77 78 79 80 81 82 83 > >>

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：