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

57,254 篇 会议
184 册 图书

馆藏范围

57,431 篇 电子文献
7 种 纸本馆藏

日期分布

学科分类号

57,042 篇 工学
- 56,774 篇 计算机科学与技术...
- 7,556 篇 控制科学与工程
- 2,463 篇 软件工程
- 2,057 篇 电气工程
- 483 篇 信息与通信工程
- 360 篇 生物医学工程（可授...
- 67 篇 机械工程
- 57 篇 土木工程
- 23 篇 石油与天然气工程
- 18 篇 生物工程
- 15 篇 仪器科学与技术
4,454 篇 理学
- 3,698 篇 数学
- 368 篇 物理学
- 274 篇 生物学
- 53 篇 科学技术史(分学科...
- 52 篇 统计学（可授理学、...
- 22 篇 系统科学
- 18 篇 化学
2,190 篇 医学
- 1,233 篇 基础医学(可授医学...
- 1,065 篇 临床医学
- 36 篇 特种医学
2,181 篇 文学
- 2,178 篇 外国语言文学
1,355 篇 管理学
- 1,256 篇 管理科学与工程(可...
- 84 篇 图书情报与档案管...
1,231 篇 教育学
- 709 篇 教育学
- 507 篇 心理学(可授教育学...
- 15 篇 体育学
57 篇 法学
- 56 篇 社会学
36 篇 艺术学
- 36 篇 音乐与舞蹈学
35 篇 哲学
- 35 篇 哲学
13 篇 经济学
1 篇 农学
1 篇 军事学

主题

1,258 篇 artificial intel...
1,112 篇 machine learning
978 篇 deep learning
919 篇 data mining
780 篇 multi agent syst...
725 篇 semantics
527 篇 classification
510 篇 reinforcement le...
474 篇 learning systems
463 篇 clustering
439 篇 neural networks
415 篇 ontology
353 篇 natural language...
257 篇 computers
249 篇 rough sets
236 篇 fuzzy sets
230 篇 feature selectio...
219 篇 computer circuit...
213 篇 knowledge repres...
205 篇 logic programmin...

机构

191 篇 univ chinese aca...
107 篇 chinese acad sci...
65 篇 harbin inst tech...
63 篇 polish acad sci ...
62 篇 wroclaw univ sci...
59 篇 soochow univ sch...
55 篇 delft univ techn...
53 篇 carnegie mellon ...
48 篇 beijing univ tec...
44 篇 chinese acad sci...
44 篇 shanghai jiao to...
43 篇 tu wien austria
42 篇 univ sci & techn...
41 篇 czech tech univ ...
40 篇 univ ulsan sch e...
39 篇 beijing jiaotong...
38 篇 tsinghua univ de...
38 篇 north carolina s...
37 篇 nanjing univ sta...
36 篇 tsinghua univ sc...

作者

47 篇 gelbukh alexande...
42 篇 wang lei
36 篇 reis luis paulo
35 篇 pelachaud cather...
35 篇 malerba donato
34 篇 liu yang
33 篇 novais paulo
33 篇 cpalka krzysztof
32 篇 li li
30 篇 ricci alessandro
27 篇 lau nuno
26 篇 wang hui
26 篇 napoli amedeo
25 篇 boryczka urszula
25 篇 rutkowski leszek
25 篇 wang jing
25 篇 pluhacek michal
25 篇 bickmore timothy
25 篇 calvo hiram
24 篇 villasenor-pined...

语言

57,321 篇 英文
116 篇 中文
1 篇 丹麦文

检索条件"丛书名=Lecture notes in artificial intelligence,"

共 57438 条记录，以下是4791-4800 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：

Critical Node Privacy Protection Based on Random Pruning of Critical Trees 1

引用

16th International Conference on Knowledge Science, Engineering and Management (KSEM)

作者： Qu, Lianwei Wang, Yong Yang, Jing Harbin Engn Univ Coll Comp Sci & Technol Harbin 150001 Heilongjiang Peoples R China

ISBN: (数字)9783031402838

ISBN: (纸本)9783031402821;9783031402838

With the popularity of social networks, the conflict between the heterogeneous social network data publishing and user privacy leakage is becoming very obvious. Especially for critical node users, if the critical node users suffer from background knowledge attacks during data publishing, it can not only lead to the privacy information leakage of the critical user but also lead to the privacy leakage of their friends. To address this issue, we propose a critical node privacy protection method based on random pruning of critical trees. First, we obtain the critical node candidate set by the degree centrality. Then, we calculate the candidate node's global and local criticality to get the critical node set. Next, we extract the critical tree with the critical node as the root node. Finally, we design a critical tree privacy protection strategy based on random pruning. The experimental results show that the proposed method can balance the privacy and availability of critical nodes in the network data publishing.

关键词： Heterogeneous social networks Node criticality Critical node Critical tree Random pruning

来源：评论

学校读者我要写书评

暂无评论

MBDNet: Mitigating the "Under-Training Issue" in Dual-Encoder Model for RGB-d Salient Object Detection 19th

MBDNet: Mitigating the "Under-Training Issue" in Dual-Encode...

引用

19th International Conference on Advanced Intelligent Computing Technology and Applications (ICIC)

作者： Wang, Shuo Yang, Gang Zhang, Yunhua Xu, Qiqi Wang, Yutao Northeastern Univ Shenyang 110819 Peoples R China DUT Artificial Intelligence Inst Dalian 116024 Peoples R China

ISBN: (纸本)9789819947607;9789819947614

Existing RGB-D salient object detection methods generally rely on the dual-encoder structure for RGB and depth feature extraction. However, we observe that the encoders in such models are often not adequately trained to obtain superior feature representations. We name this problem the "under-training issue". To this end, we propose a multi-branch decoding network (MBDNet) to suppress this issue. The MBDNet introduces additional decoding branches with supervision to form a multi-branch decoding (MBD) structure, facilitating the training of the encoders and enhancing the feature representation. Specifically, to ensure the effectiveness of the introduced supervision and improve the performance of additional decoding branches, we design an adaptive multi-scale decoding (AMSD) module. We also design a multi-branch feature aggregation (MBFA) module to aggregate the multi-branch features in MBD to further improve the detection accuracy. In addition, we design an enhancement complement fusion (ECF) module to achieve multi-modality feature fusion. Extensive experiments demonstrate that our MBDNet outperforms other state-of-the-art methods and mitigates the "under-training issue".

关键词： Salient object detection RGB-D "under-training issue" Feature fusion

来源：评论

学校读者我要写书评

暂无评论

Agent Based Model of Elementary School Group Learning - A Case Study 15th

Agent Based Model of Elementary School Group Learning - A Ca...

引用

15th International Conference on Computational Collective intelligence (ICCCI)

作者： Wedrychowicz, Barbara Maleszka, Marcin Wroclaw Univ Sci & Technol St Wyspianskiego 27 PL-50370 Wroclaw Poland

ISBN: (纸本)9783031414558;9783031414565

The paper described an agent-based model that simulate group work of elementary school children. It imitates students' characteristics and behaviours most frequently found in pedagogical literature about active and group learning. The model main objective is to forecast the change in the student's knowledge. We simulated and compared knowledge changes during individual learning and cooperative learning with different group composition. The observation of real students was carried out and compared to the outcomes of the simulations. The results are discussed in the context of improving the model by adding previously not included students' characteristics and behaviours.

关键词： Agent based modeling Teaching model Group modeling Multi-agent simulation

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Few-Shot Learning via Positive Expansions and Negative Proxies 19th

Unsupervised Few-Shot Learning via Positive Expansions and N...

引用

19th International Conference on Advanced Intelligent Computing Technology and Applications (ICIC)

作者： Chen, Liangjun Qian, Pengjiang Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi 214122 Jiangsu Peoples R China

ISBN: (纸本)9789819947607;9789819947614

Few-shot learning hasmade significant progress recently thanks to pretraining methods and meta-learning approaches. These methods, however, require an extensive labeled dataset that is difficult to obtain. We propose an unsupervised few-shot learning method based on positive expansions and negative proxies to fully utilize abundant unlabeled data. Our approach learns meaningful representations through self-supervised pre-training on unlabeled data using a simple but effective positive and negative sampling strategy. Specifically, we sort the negative queue in descending order based on similarity to the query embedding and then select the top N negatives as positive extensions. Behind these N negatives, we choose M negatives as proxies. We further incorporate this sampling strategy into a novel contrastive loss function. We learn the representation by minimizing the distance between query and positive extensions while maximizing the distance to negative proxies. Our approach greatly narrows the performance gap between supervised and unsupervised learning in twowidely used few-shot benchmarks. Under a linear evaluation protocol, our method also achieves performance comparable to current SOTA self-supervised learning methods.

关键词： Few-shot Learning Self-supervised Learning Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Aware Two-Stream Decoding for Outline-Conditioned Chinese Story Generation 1

引用

16th International Conference on Knowledge Science, Engineering and Management (KSEM)

作者： Lin, Huahai Wen, Yong Jiang, Ping Wen, Wu Liang, Xianye Guangxi Minzu Univ Sch Artificial Intelligence Nanning 530006 Peoples R China Guangxi Police Coll Sch Comp & Informat Technol Nanning 530028 Peoples R China Weibin Zhongye Informat Technol Ltd Co Nanning Peoples R China

ISBN: (数字)9783031402890

ISBN: (纸本)9783031402883;9783031402890

Generating a coherent and reasonable story for a given story outline, i.e., outline-conditioned story generation, is an important and challenging task. The key challenges of the task lie in how to ensure that the majority of the story outline points appear in the generated story sufficiently and expand the source of information for the story outline effectively, these challenges are still under-explored by prior works, especially for outline-conditioned Chinese story generation. In this paper, we propose a novel outline-conditioned Chinese story generation framework that utilizes a two-stream decoding mechanism to make sure most of the points listed in the outlines of the stories are included in the generated stories by training the generative model and generating the stories twice. Moreover, we enlarge the outline points by incorporating external knowledge from a Chinese commonsense knowledge base to generate various Chinese stories. Extensive experiments show that our framework outperforms the state-of-the-art Chinese generation models on several evaluation metrics, demonstrating the importance of the two-stream decoding mechanism and the necessity of incorporating extra Chinese knowledge into the story outline for generating more diverse Chinese stories.

关键词： Story Outline Chinese Story Generation Commonsense Knowledge Two-Stream Decoding

来源：评论

学校读者我要写书评

暂无评论

Extrinsic Calibration Framework for Camera-Lidar Fusion Using Recurrent Residual Network 15th

Extrinsic Calibration Framework for Camera-Lidar Fusion Usin...

引用

15th International Conference on Computational Collective intelligence (ICCCI)

作者： Aouragh, Massinissa Gulyas, Laszlo ELTE Eotovos Lorand Univ Fac Informat Dept Artificial Intelligence Budapest Hungary Robert Bosch Kft Budapest Hungary

ISBN: (纸本)9783031414558;9783031414565

Combining the use of 3D LiDAR's and 2D cameras is getting increasingly popular in sensor suits for perception tasks, making them two important sets of sensors for 3D object detection. Fusing the data of these two sensors results in a highly descriptive environment. However, the combination into a single representation is not straightforward due to the difference in signal characteristics and distribution. Thus the robustness of such system is highly dependent on calibration. In case of most methods the image quality is also a predominant condition for performance. This paper proposes a calibration framework in PyTorch for both KITTI and nuScenes. CalibRRNet takes monocular images and 3D depth information as input and outputs a 6 DoF rigid body transformation. Using similar architecture to ResNet18, leveraging the advantage of jumping connection, we add a recurrent network on the last stage to keep track of the previously predicted transformations. Training CalibRRNet is against photometric consistency and point cloud distance. CalibRRNet solves the geometric problem and predicts the extrinsic calibration parameters. The application of the proposed framework is not limited to only pure calibration tasks. It can also be used as a preprocessing module for camera-lidar fusion models to alleviate the need for an accurate calibration to ensure performance. Our experiments results confirm the validity of the proposed approach, with primary improvements observed on translation, but also on rotation.

关键词： Point cloud Multiple sensors camera-lidar calibration

来源：评论

学校读者我要写书评

暂无评论

A First Evolutionary Fuzzy Approach for Change Mining with Smart Bands 15th

A First Evolutionary Fuzzy Approach for Change Mining with S...

引用

15th International Conference on Flexible Query Answering Systems (FQAS)

作者： Padilla, David Padilla-Rascon, M. Asuncion Camara, Ruben Carmona, Cristobal J. Univ Jaen Dept Comp Sci Campus Las Lagunillas Jaen 23071 Spain Univ Jaen Andalusian Res Inst Data Sci & Computat Intellige Campus Las Lagunillas Jaen 23071 Spain De Montfort Univ Leicester Sch Pharm Leicester 9BH Leics England

ISBN: (纸本)9783031429347;9783031429354

Data Science is one of the most prominent interdisciplinary fields of artificial intelligence at the moment. It aims to analyze large volumes of data (big data) in complex environments in order to extract knowledge from them. In this contribution a first approach to change mining is presented. The algorithm employs an evolutionary fuzzy system and it is developed within an Android application which will allow us the incorporation and comparison of new algorithms in the future. The accompanying study is based on the analysis of data generated by wearables, more specifically smart bands, in order to discover knowledge in sleep and activity data generated by the user in different time periods.

关键词： Change mining eHealth data stream mining evolutionary fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging Queue Length and Attention Mechanisms for Enhanced Traffic Signal Control Optimization

Leveraging Queue Length and Attention Mechanisms for Enhance...

引用

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Zhang, Liang Xie, Shubin Deng, Jianming Lanzhou Univ State Key Lab Herbage Improvement & Grassland Agr Coll Ecol Lanzhou 730000 Peoples R China

ISBN: (纸本)9783031434297;9783031434303

Reinforcement learning (RL) techniques for traffic signal control (TSC) have gained increasing popularity in recent years. However, most existing RL-based TSC methods tend to focus primarily on the RL model structure while neglecting the significance of proper traffic state representation. Furthermore, some RL-based methods heavily rely on expert-designed traffic signal phase competition. In this paper, we present a novel approach to TSC that utilizes queue length as an efficient state representation. We propose two new methods: (1) Max Queue-Length (M-QL), an optimization-based traditional method designed based on the property of queue length;and (2) AttentionLight, an RL model that employs the self-attention mechanism to capture the signal phase correlation without requiring human knowledge of phase relationships. Comprehensive experiments on multiple real-world datasets demonstrate the effectiveness of our approach: (1) the M-QL method outperforms the latest RL-based methods;(2) AttentionLight achieves a new state-of-the-art performance;and (3) our results highlight the significance of proper state representation, which is as crucial as neural network design in TSC methods. Our findings have important implications for advancing the development of more effective and efficient TSC methods. Our code is released on Github (https://github. com/LiangZhang1996/AttentionLight).

关键词： traffic signal control reinforcement learning state representation attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Deep Spatiotemporal Clustering: A Temporal Clustering Approach for Multi-dimensional Climate Data

Deep Spatiotemporal Clustering: A Temporal Clustering Approa...

引用

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Faruque, Omar Nji, Francis Ndikum Cham, Mostafa Salvi, Rohan Mandar Zheng, Xue Wang, Jianwu Univ Maryland Dept Informat Syst Baltimore MD 21201 USA Lawrence Livermore Natl Lab Climate Sci Sect Livermore CA 94550 USA

ISBN: (纸本)9783031434297;9783031434303

Clustering high-dimensional spatiotemporal data using an unsupervised approach is a challenging problem for many data-driven applications. Existing state-of-the-art methods for unsupervised clustering use different similarity and distance functions but focus on either spatial or temporal features of the data. Concentrating on joint deep representation learning of spatial and temporal features, we propose Deep Spatiotemporal Clustering (DSC), a novel algorithm for the temporal clustering of high-dimensional spatiotemporal data using an unsupervised deep learning method. Inspired by the U-net architecture, DSC utilizes an autoencoder integrating CNN-RNN layers to learn latent representations of the spatiotemporal data. DSC also includes a unique layer for cluster assignment on latent representations that uses the Student's t-distribution. By optimizing the clustering loss and data reconstruction loss simultaneously, the algorithm gradually improves clustering assignments and the nonlinear mapping between low-dimensional latent feature space and high-dimensional original data space. A multivariate spatiotemporal climate dataset is used to evaluate the efficacy of the proposed method. Our extensive experiments show our approach outperforms both conventional and deep learning-based unsupervised clustering algorithms. Additionally, we compared the proposed model with its various variants (CNN encoder, CNN autoencoder, CNN-RNN encoder, CNN-RNN autoencoder, etc.) to get insight into using both the CNN and RNN layers in the autoencoder, and our proposed technique outperforms these variants in terms of clustering results.

关键词： Temporal clustering Multivariate spatiotemporal climate data Deep neural network U-net

来源：评论

学校读者我要写书评

暂无评论

A Biologically Plausible Graph Structure for AGI 15th

A Biologically Plausible Graph Structure for AGI

引用

15th International Conference on artificial General intelligence (AGI)

作者： Simon, Charles J. Future AI Washington DC 20036 USA

ISBN: (纸本)9783031199066;9783031199073;9783031199066

Graph structures have shown to represent a viable approach to developingAGI. This paper describes howa knowledge graph could be represented in neurons and introduces theUniversal Knowledge Store (UKS), an open-source implementation, which could form one component of AGI. Unlike backpropagationrelated systems which have only the most tenuous biological relationship, graph structures can be built from basic biological neuron models.

关键词： artificial general intelligence Graph algorithm Biological neuron Leaky-integrate-and-fire Hebbian synapse

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 << < 476 477 478 479 480 481 482 483 484 485 > >>

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：