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

470 篇 期刊文献
310 篇 会议
4 篇 学位论文

馆藏范围

784 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

730 篇 工学
- 488 篇 计算机科学与技术...
- 299 篇 电气工程
- 129 篇 信息与通信工程
- 97 篇 软件工程
- 63 篇 控制科学与工程
- 48 篇 仪器科学与技术
- 30 篇 电子科学与技术（可...
- 26 篇 机械工程
- 26 篇 石油与天然气工程
- 21 篇 生物医学工程（可授...
- 14 篇 测绘科学与技术
- 12 篇 动力工程及工程热...
- 10 篇 交通运输工程
- 9 篇 材料科学与工程（可...
- 9 篇 环境科学与工程（可...
- 9 篇 网络空间安全
- 7 篇 光学工程
- 6 篇 化学工程与技术
- 5 篇 土木工程
128 篇 理学
- 51 篇 物理学
- 37 篇 生物学
- 29 篇 化学
- 23 篇 数学
- 10 篇 地球物理学
- 5 篇 系统科学
88 篇 医学
- 62 篇 临床医学
- 24 篇 基础医学(可授医学...
- 14 篇 特种医学
59 篇 管理学
- 51 篇 管理科学与工程(可...
- 8 篇 图书情报与档案管...
6 篇 农学
3 篇 法学
2 篇 经济学
2 篇 教育学
1 篇 文学
1 篇 艺术学

主题

784 篇 auto-encoder
191 篇 deep learning
50 篇 feature extracti...
47 篇 anomaly detectio...
43 篇 machine learning
37 篇 unsupervised lea...
25 篇 lstm
25 篇 convolutional ne...
21 篇 neural networks
21 篇 classification
19 篇 task analysis
19 篇 deep neural netw...
19 篇 convolutional ne...
18 篇 neural network
16 篇 training
15 篇 fault diagnosis
15 篇 cnn
15 篇 extreme learning...
14 篇 clustering
14 篇 generative adver...

机构

6 篇 fuzhou univ coll...
5 篇 northeastern uni...
5 篇 univ elect sci &...
4 篇 jiangnan univ sc...
4 篇 sichuan univ col...
4 篇 yunnan univ sch ...
4 篇 air force engn u...
4 篇 northeastern uni...
4 篇 southeast univ s...
3 篇 china univ min &...
3 篇 nanjing univ sta...
3 篇 xidian univ sch ...
3 篇 tianjin univ col...
3 篇 jiangnan univ sc...
3 篇 fudan univ acad ...
3 篇 univ elect sci &...
3 篇 north china elec...
3 篇 univ sci & techn...
3 篇 shanghai jiao to...
3 篇 huazhong univ sc...

作者

6 篇 wang shiping
5 篇 liu yang
5 篇 fu yun
5 篇 zhou lihua
4 篇 cai jinyu
4 篇 li rui
4 篇 zhang wanqing
4 篇 wang xiaodan
4 篇 li shuaichao
4 篇 lei lei
4 篇 guo wenzhong
4 篇 cui ying
3 篇 xie xijiong
3 篇 fu r.
3 篇 fayyazi hossein
3 篇 zuo wenbo
3 篇 li yanfeng
3 篇 liu zhen
3 篇 xu kai
3 篇 wang li

语言

758 篇 英文
20 篇 其他
4 篇 中文
3 篇 德文
2 篇 法文
1 篇 意大利文
1 篇 朝鲜文

检索条件"主题词=Auto-Encoder"

共 784 条记录，以下是131-140 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：

EXPLORING THE RELATIONSHIPS BETWEEN SCATTERING PHYSICS AND auto-encoder LATENT-SPACE EMBEDDING

EXPLORING THE RELATIONSHIPS BETWEEN SCATTERING PHYSICS AND A...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： De, Shaunak Clanton, Christian Bickerton, Steven Baney, Oliwia Patnaik, Kaushik Orbital Insight Inc 3000 El Camino Real4th Floor Palo Alto CA 94303 USA

ISBN: (纸本)9781728163741

Polarimetric SAR (PolSAR) is uniquely able to capture structural and compositional properties of targets leading to improved performance in various classification applications over traditional single-polarization SAR. To aid in the interpretation of the return scatter, several decomposition techniques have been developed that attempt to classify the scene by presenting the return power as a combination of pre-determined canonical targets. For most decomposition techniques, these relationships are derived from the physics of radar scatter, and thus the results of the segmentation are explainable in terms of observable physical phenomena. Recently, Deep Neural Networks (DNNs) have emerged as a leading strategy for classifying PolSAR data. While effective, these techniques are dependent on discovering relationships between the data and provided supervised labels during an exploratory phase of the algorithm called "training" The inter-dependencies are embedded into the weights of the network and are subsequently used to perform classification of the unlabeled data samples. Since the entire process is data-driven, it can be difficult to explain the outcomes of the algorithm physically. In this paper, we begin to explore the relationship between radar physics and the latent space embedded in the networks during supervised training. The goal is to explore current and future possibilities of explaining the results of deep neural networks and relating their outputs to radar physics. This can help improve confidence in the outputs of DNNs and potentially illuminate strategies to further improve their performance by embedding physical constraints in their training and classification.

关键词： Polarimetry Synthetic Aperture Radar auto-encoder Neural Networks

来源：评论

学校读者我要写书评

暂无评论

A Performance Comparison of auto-encoder and Its Variants for Classification 1

A Performance Comparison of Auto-Encoder and Its Variants fo...

引用

1st International Conference on Signals and Systems (ICSigSys)

作者： Lee, Jae-Neung Kwak, Keun-Chang Chosun Univ Dept Control & Instrumentat Engn 375 Seosuk Dong Gwangju 501759 South Korea

ISBN: (纸本)9781509067480

In this paper, we present auto-encoder (AE), stacked auto-encoder (SAE) and sparse auto-encoder (SPAE) to classify gaits of horse riding for real riding coaching. The parameters of each auto-encoder are adjusted to compare the performance. The data is collected from 16 inertial sensors attached to a motion capture suit to construct a motion database. We build the motion features as the method of gaits classification with the database. The experiment shows that the performance is 95% when applied AE. SPAE was the best in terms of time and AE was the best in performance. We can apply to coaching system by each horse gait for rider under real or horse simulator environments using the SPAE algorithm.

关键词： auto-encoder stacked auto-encoder sparse auto-encoder classification

来源：评论

学校读者我要写书评

暂无评论

DEEP FEATURE EXTRACTION BASED ON SIAMESE NETWORK AND auto-encoder FOR HYPERSPECTRAL IMAGE CLASSIFICATION 39

DEEP FEATURE EXTRACTION BASED ON SIAMESE NETWORK AND AUTO-EN...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Miao, Jiajia Wang, Bin Wu, Xiaofeng Zhang, Liming Hu, Bo Zhang, Jian Qiu Fudan Univ Key Lab Informat Sci Electromagnet Waves MoE Shanghai Peoples R China Fudan Univ Sch Informat Sci & Technol Res Ctr Smart Networks & Syst Shanghai Peoples R China

ISBN: (纸本)9781538691540

Hyperspectral image classification with limited training samples has become a hot research topic recently. Though deep convolution neural network shows powerful ability for feature extraction, its good performance often relies on sufficient training data. In this paper, we propose a multi-task learning framework based on siamese network and auto-encoder to fully exploit limited labeled samples' information and obtain discriminative features for classification of hyperspectral images. A low intraclass and high interclass variability of features can be learned by metric learning using our framework. And superpixel-based 3D sample preprocessing is applied to improve the classification accuracy on the hyperspectral images' boundaries. The experimental results demonstrate that our framework can achieve competitive results compared with the state-of-the-art methods.

关键词： Siamese network auto-encoder deep feature extraction superpixel hyperspectral image classification

来源：评论

学校读者我要写书评

暂无评论

Application of Transformer with auto-encoder in Motor Imagery EEG Signals 14

Application of Transformer with Auto-Encoder in Motor Imager...

引用

14th IEEE International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Jiang, Rui Sun, Liuting Wang, Xiaoming Xu, Youyun Nanjing Univ Posts & Telecommun Coll Telecommun & Informat Engn Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781665450850

The motor imagery brain-computer interface (MI-BCI) based on motor imagery has always been the focus of scholars. However, traditional motor imagery electroencephalogram (EEG) recognition systems cannot accurately extract signals with significant or redundant features and have low classification and recognition accuracy. To overcome this difficulty, this study proposes a novel motor imagery EEG based on deep learning. This method applies the Transformer based on the attention mechanism to the field of motor imagery EEG signals, and uses auto-encoder (AE) for dimensionality reduction. The experimental results verify that the proposed method has high average classification accuracy, kappa coefficient and F1-score by comparing with the combination of Linear Discriminant Analysis (LDA) and K-Nearest Neighbor (KNN) algorithms. It is more suitable for binary classification of motor imagery.

关键词： motor imagery deep learning auto-encoder attention module transformer module

来源：评论

学校读者我要写书评

暂无评论

Iterative Imputation of Missing Data Using auto-encoder Dynamics 27th

Iterative Imputation of Missing Data Using Auto-Encoder Dyna...

引用

27th International Conference on Neural Information Processing

作者： Smieja, Marek Kolomycki, Maciej Struski, Lukasz Juda, Mateusz Figueiredo, Mario A. T. Jagiellonian Univ Fac Math & Comp Sci Krakow Poland Cracow Univ Technol Fac Mech Engn Inst Appl Informat Krakow Poland Univ Lisbon Inst Telecomunicacoes Inst Super Tecn Lisbon Portugal

ISBN: (纸本)9783030638351;9783030638368

This paper introduces an approach to missing data imputation based on deep auto-encoder models, adequate to high-dimensional data exhibiting complex dependencies, such as images. The method exploits the properties of the vector field associated to an auto-encoder, which allows to approximate the gradient of the log-density from its reconstruction error, based on which we propose a projected gradient ascent algorithm to obtain the conditionally most probable estimate of the missing values. Our approach does not require any specialized training procedure and can be used together with any auto-encoder model trained on complete data in a classical way. Experiments performed on benchmark datasets show that imputations produced by our model are sharp and realistic.

关键词： Missing data imputation Image inpainting auto-encoder Dynamical system auto-encoder's vector field

来源：评论

学校读者我要写书评

暂无评论

L2G auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention 19

L2G Auto-encoder: Understanding Point Clouds by Local-to-Glo...

引用

27th ACM International Conference on Multimedia (MM)

作者： Liu, Xinhai Han, Zhizhong Wen, Xin Liu, Yu-Shen Zwicker, Matthias Tsinghua Univ Sch Software Beijing Peoples R China Beijing Natl Res Ctr Informat Sci & Technol BNRis Beijing Peoples R China Univ Maryland Dept Comp Sci College Pk MD 20742 USA

ISBN: (纸本)9781450368896

auto-encoder is an important architecture to understand point clouds in an encoding and decoding procedure of self reconstruction. Current auto-encoder mainly focuses on the learning of global structure by global shape reconstruction, while ignoring the learning of local structures. To resolve this issue, we propose Local-to-Global auto-encoder (L2G-AE) to simultaneously learn the local and global structure of point clouds by local to global reconstruction. Specifically, L2G-AE employs an encoder to encode the geometry information of multiple scales in a local region at the same time. In addition, we introduce a novel hierarchical self-attention mechanism to highlight the important points, scales and regions at different levels in the information aggregation of the encoder. Simultaneously, L2G-AE employs a recurrent neural network (RNN) as decoder to reconstruct a sequence of scales in a local region, based on which the global point cloud is incrementally reconstructed. Our outperforming results in shape classification, retrieval and upsampling show that L2G-AE can understand point clouds better than state-of-the-art methods.

关键词： Point Cloud auto-encoder Unsupervised Learning Hierarchical Attention Interpolation Layer Recurrent Neural Network

来源：评论

学校读者我要写书评

暂无评论

Outlier Detection for Power Data Based on Contractive auto-encoder

Outlier Detection for Power Data Based on Contractive Auto-E...

引用

1st International Conference on Advanced Information Science and System (AISS)

作者： Lu, Yuan Leng, Xiaojie Xu, Kang Luan, Weiping Yang, Wei Li, Jing Weihai Power Supply Co Shandong State Grid Weihai Shandong Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781450372916

With the continuous development of data science, big data technology has been widely used in the power industry. Since the operation of the power grid is related to the whole industrial production and the stability of household electricity consumption, abnormality detection in power big data is particularly important, and the outlier data is the most important abnormal data. There are many traditional methods for power data outlier detection. However, with the continuous deepening of the construction of intelligent power grids and ubiquitous power Internet of Things platforms, the scale of power data is increasing, and the data dimension is also rising. The traditional outlier detection method is difficult to achieve better results in the face of massive power big data. In view of the large scale and high latitude of power big data, in this paper, we proposes a power data outlier detection method based on contractive auto-encoder, which learns a low-dimensional representation of high-dimensional data by learning an encoderdecoder structure and implements outlier detection. Experiments show that the proposed method can effectively realize the outlier detection of power data and achieve higher accuracy.

关键词： Outlier Detection auto-encoder Big Data

来源：评论

学校读者我要写书评

暂无评论

Stacked sparse auto-encoder for deep clustering 17

Stacked sparse auto-encoder for deep clustering

引用

IEEE Int Conf on Parallel and Distributed Processing with Applications, Big Data and Cloud Computing, Sustainable Computing and Communications, Social Computing and Networking (ISPA/BDCloud/SocialCom/SustainCom)

作者： Cai, Jinyu Wang, Shiping Guo, Wenzhong Fuzhou Univ Coll Math & Comp Sci Fuzhou 350116 Peoples R China

ISBN: (纸本)9781728143286

Deep clustering attempts to capture the feature representation that benefits the clustering issue for inputs. Although the existing deep clustering methods have achieved encouraging performance in many research fields, there still presents some shortcomings, such as the lack of consideration of local structure preservation and sparse characteristics of input data. To this end, we propose the deep stacked sparse embedded clustering method in this paper, which considers both the preservation of local structure and sparse property of inputs. The proposed network is trained to capture the feature representation for input data by the guidance of clustering km and reconstruction loss, where the reconstruction loss prevents the corruption of feature space and guarantees the local structure preservation. Besides, some sparse parameters are added to the encoder to avoid learning of meaningless features. Through simultaneously minimizing the reconstruction loss and cluster loss, the proposed network is able to jointly learn the clustering oriented feature and optimize the assignment of cluster labels. Then we conduct amounts of comparative experiments, which consist of six clustering methods and four publicly available data sets. Eventually, the clustering accuracy, adjusted rand index and normalized mutual information are utilized as three evaluation metrics to provide a comparison. Comprehensive experiments validate the effectiveness of introducing sparse property and preserving local structure in our method.

关键词： Machine learning unsupervised learning deep clustering feature representation auto-encoder

来源：评论

学校读者我要写书评

暂无评论

A Low Inertia Guided auto-encoder for Anomaly Detection in Networks 28

A Low Inertia Guided Auto-Encoder for Anomaly Detection in N...

引用

28th International Conference on Software, Telecommunications and Computer Networks (SoftCOM)

作者： Nguimbous, Yves Nsoga Ksantini, Riadh Bouhoula, Adel Higher Sch Commun Tunis Digital Secur Res Lab Tunis Tunisia Univ Bahrain Dept Comp Sci Coll IT Zallaq Bahrain Arabian Gulf Univ Coll Grad Studies Manama Bahrain

ISBN: (纸本)9789532900996

In the case of One-class classification, the low variance directions tend to be more informative to build a model on target class. This paper introduces a low Inertia auto-encoder for anomaly detection. The proposed model emphasizes the low Inertia when training the network with gradient descent algorithm. The low Inertia auto-encoder model is able to improve upon the classical auto-encoder by incorporating a regularization term into the loss function, which is the Inertia of low dimensional data embedded in the auto-encoder hidden layer. Experimental results, on KDDCup99 network traffic connections and Aegean WiFi Intrusion Dataset, have demonstrated clearly that our method has provided significantly better detection performance than the classical auto-encoder. In fact, low inertia auto-encoder allows better separation between reconstruction error distributions of normal data and anomalies.

关键词： auto-encoder Variance Inertia One-class Classification Anomaly/Intrusion Detection

来源：评论

学校读者我要写书评

暂无评论

Stochastic Decorrelation Constraint Regularized auto-encoder for Visual Recognition

Stochastic Decorrelation Constraint Regularized Auto-Encoder...

引用

23rd International Conference on MultiMedia Modeling (MMM)

作者： Mao, Fengling Xiong, Wei Du, Bo Zhang, Lefei Wuhan Univ Sch Comp Wuhan Hubei Peoples R China Collaborat Innovat Ctr Geospatial Technol Wuhan Hubei Peoples R China

ISBN: (纸本)9783319518145;9783319518138

Deep neural networks have achieved state-of-the-art performance on many applications such as image classification, object detection and semantic segmentation. But the difficulty of optimizing the networks still exists when training networks with a huge number of parameters. In this work, we propose a novel regularizer called stochastic decorrelation constraint (SDC) imposed on the hidden layers of the large networks, which can significantly improve the networks' generalization capacity. SDC reduces the co-adaptions of the hidden neurons in an explicit way, with a clear objective function. In the meanwhile, we show that training the network with our regularizer has the effect of training an ensemble of exponentially many networks. We apply the proposed regularizer to the auto-encoder for visual recognition tasks. Compared to the auto-encoder without any regularizers, the SDC constrained auto-encoder can extract features with less redundancy. Comparative experiments on the MNIST database and the FERET database demonstrate the superiority of our method. When reducing the size of training data, the optimization of the network becomes much more challenging, yet our method shows even larger advantages over the conventional methods.

关键词： Deep learning Visual recognition auto-encoder

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79页 << < 10 11 12 13 14 15 16 17 18 19 > >>

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：