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

154 篇 期刊文献
84 篇 会议

馆藏范围

238 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

223 篇 工学
- 148 篇 计算机科学与技术...
- 80 篇 电气工程
- 26 篇 控制科学与工程
- 26 篇 软件工程
- 23 篇 信息与通信工程
- 15 篇 仪器科学与技术
- 12 篇 机械工程
- 8 篇 电子科学与技术（可...
- 8 篇 生物医学工程（可授...
- 6 篇 石油与天然气工程
- 5 篇 土木工程
- 4 篇 材料科学与工程（可...
- 4 篇 安全科学与工程
- 3 篇 动力工程及工程热...
- 3 篇 建筑学
- 2 篇 光学工程
45 篇 理学
- 19 篇 生物学
- 10 篇 物理学
- 9 篇 数学
- 9 篇 化学
- 4 篇 地球物理学
- 3 篇 地质学
27 篇 管理学
- 23 篇 管理科学与工程(可...
- 3 篇 图书情报与档案管...
26 篇 医学
- 10 篇 基础医学(可授医学...
- 10 篇 临床医学
- 4 篇 特种医学
6 篇 农学
4 篇 经济学
- 3 篇 应用经济学
- 2 篇 理论经济学
3 篇 法学
- 2 篇 法学
2 篇 教育学
2 篇 艺术学
1 篇 文学

主题

238 篇 deep autoencoder
29 篇 deep learning
24 篇 anomaly detectio...
24 篇 feature extracti...
9 篇 machine learning
7 篇 transfer learnin...
7 篇 deep neural netw...
7 篇 fault detection
7 篇 unsupervised lea...
6 篇 fault diagnosis
6 篇 dimensionality r...
6 篇 neural networks
6 篇 convolutional ne...
5 篇 reinforcement le...
5 篇 deep neural netw...
4 篇 representation l...
4 篇 random forest
4 篇 graph regulariza...
4 篇 multi-view clust...
4 篇 prediction

机构

4 篇 tampere univ uni...
4 篇 univ chinese aca...
3 篇 jozef stefan ins...
2 篇 univ chinese aca...
2 篇 giet univ sch en...
2 篇 guizhou univ sch...
2 篇 guangxi univ sch...
2 篇 princess nourah ...
2 篇 xi an jiao tong ...
2 篇 northwestern pol...
2 篇 univ sydney busi...
2 篇 tulane univ ctr ...
2 篇 emory univ atlan...
2 篇 sejong univ
2 篇 inst appl math &...
2 篇 univ oviedo elec...
2 篇 hunan normal uni...
2 篇 belarusian state...
2 篇 natl univ def te...
2 篇 tulane univ dept...

作者

4 篇 mishra krishna m...
4 篇 huhtala kalevi j...
3 篇 diaz ignacio
3 篇 loncarevic zvezd...
3 篇 gams andrej
3 篇 krogerus tomi r.
2 篇 wei hong-quan
2 篇 bilodeau guillau...
2 篇 roy pankaj raj
2 篇 lam fan
2 篇 gao junbin
2 篇 hussain tanveer
2 篇 xiang yang
2 篇 pan yu
2 篇 pan zhisong
2 篇 petrovsky alexan...
2 篇 naeini saeed sav...
2 篇 nayak dillip ran...
2 篇 liu liu
2 篇 becker martin

语言

231 篇 英文
5 篇 其他
1 篇 法文
1 篇 朝鲜文
1 篇 中文

检索条件"主题词=Deep Autoencoder"

共 238 条记录，以下是201-210 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：

Accelerating Robot Reinforcement Learning with Accumulation of Knowledge

Accelerating Robot Reinforcement Learning with Accumulation ...

引用

30th International Conference on Robotics in Alpe-Adria-Danube Region (RAAD)

作者： Loncarevic, Zvezdan Gams, Andrej Jozef Stefan Inst Jamova Cesta 39 Ljubljana 1000 Slovenia Jozef Stefan Int Postgrad Sch Jamova Cesta 39 Ljubljana 1000 Slovenia

ISBN: (纸本)9783030752613;9783030752590;9783030752583

Reinforcement Learning (RL) can be applied in robotics to refine robot skills, but it may take several tens or even hundreds of attempts, which are typically just forgotten. In this paper, we show how all learning attempts, even those that do not fulfill the intended task, can be used to accelerate RL on the long-run. In a manner of non-continual lifelong learning we re-train a deep neural network that maps between the desired target/action outcome and the action in order to provide an initial estimate. Furthermore, for even faster learning, it is performed in reduced - latent space of a deep autoencoder. Robot throwing experiments clearly indicate, that the proposed methodology accelerates RL.

关键词： deep autoencoder Reinforcement learning Neural networks Robotic throwing

来源：评论

学校读者我要写书评

暂无评论

Fast Data Driven Estimation of Cluster Number in Multiplex Images using Embedded Density Outliers

Fast Data Driven Estimation of Cluster Number in Multiplex I...

引用

IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (IEEE CIBCB)

作者： Thomas, Spencer Angus Univ Surrey Dept Comp Sci Guildford Surrey England Natl Phys Lab NPL Data Sci Teddington Middx England

ISBN: (数字)9781665484626

ISBN: (纸本)9781665484626

The usage of chemical imaging technologies is becoming a routine accompaniment to traditional methods in pathology. Significant technological advances have developed these next generation techniques to provide rich, spatially resolved, multidimensional chemical images. The rise of digital pathology has significantly enhanced the synergy of these imaging modalities with optical microscopy and immunohistochemistry, enhancing our understanding of the biological mechanisms and progression of diseases. Techniques such as imaging mass cytometry provide labelled multidimensional (multiplex) images of specific components used in conjunction with digital pathology techniques. These powerful techniques generate a wealth of high dimensional data that create significant challenges in data analysis. Unsupervised methods such as clustering are an attractive way to analyse these data, however, they require the selection of parameters such as the number of clusters. Here we propose a methodology to estimate the number of clusters in an automatic data-driven manner using a deep sparse autoencoder to embed the data into a lower dimensional space. We compute the density of regions in the embedded space, the majority of which are empty, enabling the high density regions (i.e. clusters) to be detected as outliers and provide an estimate for the number of clusters. This framework provides a fully unsupervised and data-driven method to analyse multidimensional data. In this work we demonstrate our method using 45 multiplex imaging mass cytometry datasets. Moreover, our model is trained using only one of the datasets and the learned embedding is applied to the remaining 44 images providing an efficient process for data analysis. Finally, we demonstrate the high computational efficiency of our method which is two orders of magnitude faster than estimating via computing the sum squared distances as a function of cluster number.

关键词： Clustering Data driven analysis multiplex imaging deep autoencoder transfer learning hyperspectral data

来源：评论

学校读者我要写书评

暂无评论

Ensemble of DAEs for Fault Detection of Gas Turbine Engines 4

Ensemble of DAEs for Fault Detection of Gas Turbine Engines

引用

4th International Conference on System Reliability and Safety Engineering (SRSE)

作者： Ma, Shuai Wu, Yafeng Zheng, Hua Northwestern Polytech Univ Power & Energy Coll Xian Peoples R China

ISBN: (纸本)9781665473880

Aiming at the problem of limited fault-type samples, an ensemble of deep autoencoders (DAE) based fault detection approach for gas turbine engines was proposed. The proposed structure first transferred the measurement features into residual features through the physical model of gas turbine engines. Then a set of one-class classifiers based on DAEs and one-class support vector machines (OCSVM) were constructed as the base classifiers of the ensemble. The final prediction result was determined by majority voting. This structure only uses the flight data of the engine under health conditions and limited degraded conditions. The fault detection system was simulated using a dynamic model of a twin-shaft turbofan engine. The results show that the proposed approach can obtain more accurate and reliable fault detection results than the compared fault detection algorithms.

关键词： deep autoencoder one-class classification fault detection gas turbine engine ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Learning deep Embedding for Community Detection

Learning Deep Embedding for Community Detection

引用

International Conference on Big Data and Artificial Intelligence and Software Engineering (ICBASE)

作者： Pan, Yu Yang, Jiupeng Wang, Shuaihui Zou, Junhua Hu, Guyu Pan, Zhisong Army Engn Univ Nanjing Peoples R China Natl Univ Def Technol Changsha Peoples R China

ISBN: (纸本)9781728196190

Community detection is a classic and challenging network analysis task. Inspired by the similarity between autoencoder and modularity maximization model in terms of a low-dimensional approximation of the modularity matrix. In this paper, a novel community detection framework via deep autoencoder was proposed. Firstly, the modularity is fed into the autoencoder, which can obtain a non-linear deep representation for the network. In addition, node attribute similarity was utilized to construct pairwise constraints on nodes, and then a graph regularization is introduced into the framework. The extensive experimental evaluations on real-world networks and synthetic networks demonstrate that the proposed framework achieves superior performance compared with the state-of-the-art community detection algorithms.

关键词： community detection deep autoencoder modularity maximization model node attributes

来源：评论

学校读者我要写书评

暂无评论

GTDNN-Based Voice Conversion Using DAEs with Binary Distributed Hidden Units 11

GTDNN-Based Voice Conversion Using DAEs with Binary Distribu...

引用

11th International Symposium on Chinese Spoken Language Processing (ISCSLP)

作者： Ding, Yi-Yang Hu, Ya-Jun Ling, Zhen-Hua Univ Sci & Technol China Natl Engn Lab Speech & Language Informat Proc Hefei Anhui Peoples R China

ISBN: (纸本)9781538656273

This paper proposes a method that adopts deep autoencoders with binary distributed hidden units (BDAE) as feature extractors in generatively trained DNNs (GTDNN) for voice conversion (VC). In this method, the source and target speakers are modeled separately by two BDAEs, and the extracted high-level features are used to train a Bernoulli bidirectional associated memory network (BBAM) for feature mapping. Then, the estimated model parameters are copied to construct a DNN for voice conversion. Compared with other neural network-based features extractors, such as deep belief networks (DBN) and conventional deep autoencoders (DAE), BDAEs can obtain a better balance between reconstruction error and the degree of binarization of hidden units. Our experimental results show that the GTDNN using BDAEs achieved better naturalness and similarity of converted speech than the ones using DBNs and conventional DAEs. Further experiments show the BDAE model for target speaker played a more important role than the one for source speaker.

关键词： voice conversion deep neural network deep autoencoder feature extraction

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT Security: Federated Learning with GANs for Effective Attack Detection 20

Enhancing IoT Security: Federated Learning with GANs for Eff...

引用

20th International Bhurban Conference on Applied Sciences and Technology (IBCAST)

作者： Saeed, Bakhtawar Arshad, Sobia Saeed, Sanay Muhammad Umar Azam, Muhammad Awais UET Taxila Comp Engn Dept Taxila Pakistan UET Taxila Natl Ctr Cyber Secur NCCS Deep Packet Inspect Lab DPI Taxila Pakistan Whitecliffe Sch Informat Technol Technol Innovat Res Grp Auckland New Zealand

ISBN: (纸本)9798350308266;9798350308259

The rapid proliferation of the Internet of Things (IoT) has given rise to security challenges, necessitating the real-time detection and mitigation of cyberattacks. Federated Learning (FL) is promising because it enables collaborative global model training in IoT for attack detection while maintaining data privacy. However, FL-enabled systems for IoT face challenges related to class imbalance, inconsistent data distributions, and increased training time. This paper presents a novel FL-enabled approach for IoT attack detection that effectively resolves class imbalance by utilizing Generative Adversarial Networks (GANs). The proposed approach also handles non-iid data distributions through the implementation of Vertical FL. Additionally, ordinal encoding techniques are employed to enhance detection accuracy. The effectiveness of the proposed approach is extensively evaluated on the ToN-IoT and N-BaIoT datasets, the DAEs and MLPs both deep learning (DL) algorithms consistently models achieve high precision, recall, and F1 score on ToN-IoT (MLPs: 99.39%, DAEs: 99.62%) and N-BaIoT datasets (DAEs: 93.66%, MLPs: 94.63%), demonstrating its capability in improving attack detection accuracy and mitigating the limitations of FL-enabled systems in IoT scenarios.

关键词： Federated learning IoT deep autoencoder Anomaly detection Multilayer perceptron

来源：评论

学校读者我要写书评

暂无评论

deep Anomaly Detection on Attributed Networks 19

Deep Anomaly Detection on Attributed Networks

引用

SIAM International Conference on Data Mining (SDM)

作者： Ding, Kaize Li, Jundong Bhanushali, Rohit Liu, Huan Arizona State Univ Comp Sci & Engn Tempe AZ 85281 USA

ISBN: (纸本)9781611975673

Attributed networks are ubiquitous and form a critical component of modern information infrastructure, where additional node attributes complement the raw network structure in knowledge discovery. Recently, detecting anomalous nodes on attributed networks has attracted an increasing amount of research attention, with broad applications in various high-impact domains, such as cybersecurity, finance, and healthcare. Most of the existing attempts, however, tackle the problem with shallow learning mechanisms by ego-network or community analysis, or through subspace selection. Undoubtedly, these models cannot fully address the computational challenges on attributed networks. For example, they often suffer from the network sparsity and data nonlinearity issues, and fail to capture the complex interactions between different information modalities, thus negatively impact the performance of anomaly detection. To tackle the aforementioned problems, in this paper, we study the anomaly detection problem on attributed networks by developing a novel deep model. In particular, our proposed deep model: (1) explicitly models the topological structure and nodal attributes seamlessly for node embedding learning with the prevalent graph convolutional network (GCN);and (2) is customized to address the anomaly detection problem by virtue of deep autoencoder that leverages the learned embeddings to reconstruct the original data. The synergy between GCN and autoencoder enables us to spot anomalies by measuring the reconstruction errors of nodes from both the structure and the attribute perspectives. Extensive experiments on real-world attributed network datasets demonstrate the efficacy of our proposed algorithm.

关键词： Anomaly Detection Attributed Networks Graph Convolutional Network deep autoencoder

来源：评论

学校读者我要写书评

暂无评论

TOINet: Transfer Learning from Overt Speech- to Imagined Speech-Based EEG Signals with Convolutional autoencoder

TOINet: Transfer Learning from Overt Speech- to Imagined Spe...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Lee, Dae-Hyeok Kim, Sung-Jin Han, Hyeon-Taek Lee, Seong-Whan Korea University Department of Brain and Cognitive Engineering Seoul Korea Republic of Korea University The Department of Artificial Intelligence Seoul Korea Republic of

ISBN: (纸本)9798350337020

Brain-computer interface (BCI) enables the communication between humans and devices by reflecting humans' intentions and status. Endogenous BCI is the imagined-based BCI and it has the advantage that the fatigue level of the body, especially the eyes, is relatively low and no additional equipment for offering stimulation is required. When conducting imagined speech, one of the endogenous BCI paradigms, the users imagine the pronunciation as if actually speaking. In contrast, overt speech is that the users directly pronounce the words. We proposed the transfer learning-based method from overt speech- to imagined speech-based electroencephalogram (EEG) signals (TOINet). The proposed method utilizes an encoder to extract the feature vector of imagined speech from EEG signals, which is subsequently reconstructed into overt speech signals using the decoder. Through this process, the model can identify the significant and common features present in EEG signals for both overt and imagined speech, facilitating the classification of EEG signals associated with imagined speech. Eight subjects participated in the experiment. The average accuracy of the TOINet was 0.4841 for classifying four words and the EEG features of overt speech improved the performance by 0.0742. Hence, we demonstrated that EEG features of overt speech could improve the decoding performance of imagined speech. © 2023 IEEE.

关键词： Brain-computer interface (BCI) deep autoencoder Electroen-cephalogram (EEG) Imagined speech Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Automatic Character Motion Style Transfer via autoencoder Generative Model and Spatio-Temporal Correlation Mining 2nd

Automatic Character Motion Style Transfer via Autoencoder Ge...

引用

2nd CCF Chinese Conference on Computer Vision (CCCV)

作者： Hu, Dong Liu, Xin Peng, Shujuan Zhong, Bineng Du, Jixiang Huaqiao Univ Dept Comp Sci Xiamen 361021 Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen 361021 Peoples R China

ISBN: (纸本)9789811072994;9789811072987

The style of motion is essential for virtual characters animation, and it is significant to generate motion style efficiently in computer animation. In this paper, we present an efficient approach to automatically transfer motion style by using autoencoder generative model and spatio-temporal correlation mining, which allows users to transform an input motion into a new style while preserving its original content. To this end, we introduce a history vector of previous motion frames into autoencoder generative network, and extract the spatio-temporal feature of input motion. Accordingly, the spatio-temporal correlation within motions can be represented by the correlated hidden units in this network. Subsequently, we established the constraints of Gram matrix in such feature space to produce transferred motion by pre-trained generative model. As a result, various motions of particular semantic can be automatically transferred from one style to another one, and the extensive experiments have shown its outstanding performance.

关键词： deep autoencoder Style transfer Character animation Spatio-temporal correlation History vector

来源：评论

学校读者我要写书评

暂无评论

Adversarially Learned Abnormal Trajectory Classifier 16

Adversarially Learned Abnormal Trajectory Classifier

引用

16th Conference on Computer and Robot Vision (CRV)

作者： Roy, Pankaj Raj Bilodeau, Guillaume-Alexandre Polytech Montreal LITIV Lab Montreal PQ Canada

ISBN: (纸本)9781728118383

We address the problem of abnormal event detection from trajectory data. In this paper, a new adversarial approach is proposed for building a deep neural network binary classifier, trained in an unsupervised fashion, that can distinguish normal from abnormal trajectory-based events without the need for setting manual detection threshold. Inspired by the generative adversarial network (GAN) framework, our GAN version is a discriminative one in which the discriminator is trained to distinguish normal and abnormal trajectory reconstruction errors given by a deep autoencoder. With urban traffic videos and their associated trajectories, our proposed method gives the best accuracy for abnormal trajectory detection. In addition, our model can easily be generalized for abnormal trajectory-based event detection and can still yield the best behavioural detection results as demonstrated on the CAVIAR dataset.

关键词： deep autoencoder Unsupervised learning Abnormal event detection Generative adversarial networks

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24页 << < 15 16 17 18 19 20 21 22 23 24 > >>

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：