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

2,553 篇 期刊文献
1,644 篇 会议
44 篇 学位论文
2 册 图书
1 篇 资讯

馆藏范围

4,244 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,895 篇 工学
- 2,430 篇 计算机科学与技术...
- 1,574 篇 电气工程
- 678 篇 信息与通信工程
- 413 篇 控制科学与工程
- 376 篇 软件工程
- 264 篇 仪器科学与技术
- 164 篇 生物医学工程（可授...
- 161 篇 机械工程
- 151 篇 测绘科学与技术
- 139 篇 电子科学与技术（可...
- 93 篇 石油与天然气工程
- 76 篇 环境科学与工程（可...
- 71 篇 动力工程及工程热...
- 69 篇 交通运输工程
- 65 篇 材料科学与工程（可...
- 62 篇 土木工程
- 58 篇 化学工程与技术
- 58 篇 网络空间安全
- 40 篇 生物工程
- 34 篇 力学（可授工学、理...
850 篇 理学
- 283 篇 物理学
- 243 篇 生物学
- 148 篇 化学
- 137 篇 地球物理学
- 123 篇 数学
542 篇 医学
- 342 篇 临床医学
- 123 篇 基础医学(可授医学...
- 83 篇 特种医学
365 篇 管理学
- 309 篇 管理科学与工程(可...
- 36 篇 图书情报与档案管...
74 篇 农学
21 篇 经济学
18 篇 法学
14 篇 艺术学
13 篇 文学
11 篇 教育学
3 篇 哲学
1 篇 军事学

主题

4,244 篇 autoencoder
1,034 篇 deep learning
430 篇 anomaly detectio...
363 篇 machine learning
236 篇 feature extracti...
153 篇 convolutional ne...
152 篇 unsupervised lea...
149 篇 neural network
128 篇 neural networks
109 篇 training
107 篇 lstm
105 篇 classification
103 篇 dimensionality r...
82 篇 cnn
79 篇 representation l...
79 篇 clustering
77 篇 transfer learnin...
77 篇 decoding
77 篇 deep neural netw...
67 篇 convolutional ne...

机构

16 篇 univ chinese aca...
10 篇 cent south univ ...
10 篇 univ elect sci &...
9 篇 chongqing univ c...
9 篇 univ chinese aca...
9 篇 northwestern pol...
9 篇 iiit delhi new d...
9 篇 nanyang technol ...
8 篇 hong kong polyte...
8 篇 cent south univ ...
8 篇 tianjin univ col...
8 篇 univ elect sci &...
8 篇 korea adv inst s...
8 篇 peng cheng lab p...
7 篇 china univ geosc...
7 篇 chinese acad sci...
7 篇 harbin engn univ...
6 篇 queens univ dept...
6 篇 new jersey inst ...
6 篇 tsinghua univ de...

作者

20 篇 majumdar angshul
13 篇 wang wei
7 篇 zhang lin
7 篇 zhang lei
7 篇 wang jian
7 篇 wang hao
7 篇 liu li
7 篇 li bin
7 篇 kim jin-young
7 篇 hoydis jakob
7 篇 chen wei
7 篇 cho sung-bae
7 篇 gao lianru
7 篇 zhang wei
7 篇 guo lei
6 篇 wang lei
6 篇 li li
6 篇 wang kai
6 篇 li yuan
6 篇 liu jie

语言

4,082 篇 英文
101 篇 其他
34 篇 中文
7 篇 法文
6 篇 德文
6 篇 土耳其文
2 篇 朝鲜文
1 篇 西班牙文
1 篇 意大利文
1 篇 日文
1 篇 葡萄牙文

检索条件"主题词=autoencoder"

共 4244 条记录，以下是4121-4130 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：

INCLUSION OF MANNER OF ARTICULATION TO ACHIEVE IMPROVED PHONEME CLASSIFICATION ACCURACY FOR BENGALI CONTINUOUS SPEECH 20

INCLUSION OF MANNER OF ARTICULATION TO ACHIEVE IMPROVED PHON...

引用

20th Conference of the Oriental-Chapter-of-the-International-Coordinating-Committee-on-Speech-Databases-and-Speech-I/O-Systems-and-Assessment (O-COCOSDA)

作者： Bhowmik, Tanmay Mandal, Shyamal Kumar Das Univ Petr & Energy Studies SOCSE Dehra Dun Uttar Pradesh India IIT Kharagpur CET Kharagpur W Bengal India

ISBN: (纸本)9781538633335

In this experiment, a phoneme classification model has been developed using a Deep Neural Network based framework. The experiment is conducted in two phases. In the first phase, phoneme classification task has been performed. The deep-structured model provided good overall classification accuracy of 87.8%. All the phonemes are classified with precision and recall values. A confusion matrix of all the Bengali phonemes is derived. Using the confusion matrix, the phonemes are classified into nine groups. These nine groups provided better overall classification accuracy of 98.7%, and a new confusion matrix is derived for this nine groups. A lower confusion rate is observed this time. In the second phase of the experiment, the nine groups are reclassified into 15 groups using the manner of articulation based knowledge and the deep-structured model is retrained. The system provided 98.9% of overall classification accuracy this time. This result is almost equal to the overall accuracy which was observed for nine groups. But as the nine groups are redivided into 15 groups, the phoneme confusion in a single group became less which leads to a better phoneme classification model.

关键词： Bengali phoneme classification manner of articulation phoneme confusion matrix deep neural network autoencoder

来源：评论

学校读者我要写书评

暂无评论

NEURAL NETWORK HYPERSPECTRAL UNMIXING WITH SPECTRAL INFORMATION DIVERGENCE OBJECTIVE 37

NEURAL NETWORK HYPERSPECTRAL UNMIXING WITH SPECTRAL INFORMAT...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Palsson, Frosti Sigurdsson, Jakob Sveinsson, Johannes R. Ulfarsson, Magnus O. Univ Iceland Fac Elect & Comp Engn Hjardarhagi 2-6 IS-107 Reykjavik Iceland

ISBN: (纸本)9781509049516

Hyperspectral unmixing is a challenging inverse problem that involves determining the fractional abundances of the representive material (endmembers) in each pixel. In this paper, we develop a neural network autoencoder, that dynamically exploits the sparsity of the abundances and enforces the abundance sum constraint (ASC) for hyperspectral unmixing. Instead of using the conventional mean square error (MSE) objective function, we use the spectral information divergence (SID) measure. Experiments are performed using a real hyperspectral dataset and we compare results obtained using both MSE and SID. It is demonstrated by qualitative inspection that using SID gives significantly better results than using MSE.

关键词： Hyperspectral unmixing autoencoder deep learning neural network spectral information divergence

来源：评论

学校读者我要写书评

暂无评论

Using deep networks for fraud detection in the credit card transactions 4

Using deep networks for fraud detection in the credit card t...

引用

IEEE 4th International Conference on Knowledge-Based Engineering and Innovation (KBEI)

作者： Kazemi, Zahra Zarrabi, Houman Islamic Azad Univ Sci & Res Tehran Iran Iran ICT Res Ctr Sci & Res Tehran Iran

ISBN: (纸本)9781538626405

Deep learning is a very noteworthy technic that is take into consideration in the several fields. One of the most attractive subjects that need more attention in the prediction accuracy is fraud detection. As the deep network can gradually learn the concepts of any complicated problem, using this technic in this realm is very beneficial. To do so, we propose a deep autoencoder to extract best features from the information of the credit card transactions and then append a softmax network to determine the class labels. Regarding the effect of features in such data employing an overcomplete autoencoder can map data to a high dimensional space and using the sparse models leads to be in a discriminative space that is useful for classification aims. The benefit of this method is the generality virtues that we can use such networks in several realms e.g. national intelligence, cyber security, marketing, medical informatics and so on. Another advantage is the ability to facing big datasets. As the learning phase is offline we can use it for a huge amount of data and generalize that is earned. Results can reveal the advantages of proposed method comparing to the state of the arts.

关键词： Credit card transactions fraud detection deep networks autoencoder

来源：评论

学校读者我要写书评

暂无评论

MagNet: a Two-Pronged Defense against Adversarial Examples 17

MagNet: a Two-Pronged Defense against Adversarial Examples

引用

24th ACM-SIGSAC Conference on Computer and Communications Security (ACM CCS)

作者： Meng, Dongyu Chen, Hao ShanghaiTech Univ Shanghai Peoples R China Univ Calif Davis Davis CA 95616 USA

ISBN: (纸本)9781450349468

Deep learning has shown impressive performance on hard perceptual problems. However, researchers found deep learning systems to be vulnerable to small, specially crafted perturbations that are imperceptible to humans. Such perturbations cause deep learning systems to mis-classify adversarial examples, with potentially disastrous consequences where safety or security is crucial. Prior defenses against adversarial examples either targeted specific attacks or were shown to be ineffective. We propose MagNet, a framework for defending neural network classifiers against adversarial examples. MagNet neither modifies the protected classifier nor requires knowledge of the process for generating adversarial examples. MagNet includes one or more separate detector networks and a reformer network. The detector networks learn to differentiate between normal and adversarial examples by approximating the manifold of normal examples. Since they assume no specific process for generating adversarial examples, they generalize well. The reformer network moves adversarial examples towards the manifold of normal examples, which is effective for correctly classifying adversarial examples with small perturbation. We discuss the intrinsic difficulties in defending against whitebox attack and propose a mechanism to defend against gray-box attack. Inspired by the use of randomness in cryptography, we use diversity to strengthen MagNet. We show empirically that MagNet is effective against the most advanced state-of-the-art attacks in blackbox and graybox scenarios without sacrificing false positive rate on normal examples.

关键词： adversarial example neural network autoencoder

来源：评论

学校读者我要写书评

暂无评论

Predicting Latent Structured Intents from Shopping Queries 17

Predicting Latent Structured Intents from Shopping Queries

引用

26th International Conference on World Wide Web (WWW)

作者： Wu, Chao-Yuan Ahmed, Amr Kumar, Gowtham Ramani Datta, Ritendra UT Austin Comp Sci Austin TX 78712 USA Google Mountain View CA USA

ISBN: (纸本)9781450349130

In online shopping, users usually express their intent through search queries. However, these queries are often ambiguous. For example, it is more likely (and easier) for users to write a query like "high-end bike" than "21 speed carbon frames jamis or giant road bike". It is challenging to interpret these ambiguous queries and thus search result accuracy suffers. A user oftentimes needs to go through the frustrating process of refining search queries or self-teaching from possibly unstructured information. However, shopping is indeed a structured domain, that is composed of category hierarchy, brands, product lines, features, etc. It would be much better if a shopping site could understand users' intent through this structure, present organized information, and then find the items with the right categories, brands or features. In this paper we study the problem of inferring the latent intent from unstructured queries and mapping them to structured attributes. We present a novel framework that jointly learns this knowledge from user consumption behaviors and product metadata. We present a hybrid Long Shortterm Memory (LSTM) [10] joint model that is accurate and robust, even though user queries are noisy and product catalog is rapidly growing. Our study is conducted on a largescale dataset from Google Shopping, that is composed of millions of items and user queries along with their click responses. Extensive qualitative and quantitative evaluation shows that the proposed model is more accurate, concise, and robust than multiple possible alternatives. In terms of information retrieval (IR) performance, our model is able to improve the quality of current Google Shopping production system, which is a very strong baseline.

关键词： query understanding entity relationship modeling autoencoder recurrent neural networks shopping

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Feature Learning for EEG-based Emotion Recognition

Unsupervised Feature Learning for EEG-based Emotion Recognit...

引用

International Conference on Cyberworlds (CW)

作者： Lan, Zirui Sourina, Olga Wang, Lipo Scherer, Reinhold Mueller-Putz, Gernot Nanyang Technol Univ Fraunhofer Singapore Singapore Singapore Nanyang Technol Univ Sch Elect & Elect Engn Singapore Singapore Graz Univ Technol Inst Neural Engn Graz Austria

ISBN: (纸本)9780769562155

Spectral band power features are one of the most widely used features in the studies of electroencephalogram (EEG)-based emotion recognition. The power spectral density of EEG signals is partitioned into different bands such as delta, theta, alpha and beta band etc. Though based on neuroscientific findings, the partition of frequency bands is somewhat on an adhoc basis, and the definition of frequency ranges of the bands of interest can vary between studies. On the other hand, it is also arguable that one definition of power bands could perform equally well on all subjects. In this paper, we propose to use autoencoder to automatically learn from each subject the salient frequency components from power spectral density estimated as periodogram by Fast Fourier Transform (FFT). We propose a network architecture especially for EEG feature extraction, one that adopts hidden unit clustering with added pooling neuron per cluster. The classification accuracy with features extracted by our proposed method is benchmarked against that with standard power features. Experimental results show that our proposed feature extraction method achieves accuracy ranging from 44% to 59% for three-emotion classification. We also see a 4-20% accuracy improvement over standard band power features.

关键词： emotion classification electroencephalogram (EEG) brain-computer-interface (BCI) power spectral density unsupervised feature extraction autoencoder

来源：评论

学校读者我要写书评

暂无评论

Representation Learning with Pair-wise Constraints for Collaborative Ranking 17

Representation Learning with Pair-wise Constraints for Colla...

引用

10th ACM International Conference on Web Search and Data Mining (WSDM)

作者： Zhuang, Fuzhen Luo, Dan Yuan, Nicholas Jing Xie, Xing He, Qing Chinese Acad Sci ICT Key Lab Intelligent Informat Proc Beijing Peoples R China Microsoft Res 5 Danling St Beijing Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

ISBN: (纸本)9781450346757

Last decades have witnessed a vast amount of interest and research in recommendation systems. Collaborative filtering which uses the known preferences of a group of users to make recommendations or predictions of the unknown preferences for other users, is one of the most successful approaches to build recommendation systems. Most previous collaborative filterin approaches employ the matrix factorization techniques to learn latent user feature profile and item feature profiles Also many subsequent works are proposed to incorporate users' social network information and items' attributions to further improve recommendation performance under the matrix factorization framework. However, the matrix factorization based methods may not make full use of the rating information, leading to unsatisfying performance. Recently deep learning has been approved to be able to fin good representations in natural language processing, image classification and so on. Along this line, we propose a collaborative ranking framework via REpresent4tion learning with Pair-wise constraints (REAP for short), in which autoencoder is used to simultaneously learn the latent factors of both users and items and pair-wise ranked loss define by (user, item) pairs is considered. Extensive experiments are conducted on five data sets to demonstrate the effectiveness of the proposed framework.

关键词： Collaborative Ranking autoencoder Representation Learning Pair-wise Constraints

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Modeling and Prediction in Cellular Networks: A Big Data Enabled Deep Learning Approach

Spatiotemporal Modeling and Prediction in Cellular Networks:...

引用

IEEE Conference on Computer Communications (IEEE INFOCOM)

作者： Wang, Jing Tang, Jian Xu, Zhiyuan Wang, Yanzhi Xue, Guoliang Zhang, Xing Yang, Dejun Syracuse Univ Dept Elect Engn & Comp Sci Syracuse NY 13244 USA Arizona State Univ Ira A Fulton Sch Engn Tempe AZ 85287 USA BUPT Key Lab Universal Wireless Commun Beijing Peoples R China Beijing Univ Technol BJUT Beijing Adv Innovat Ctr Future Internet Technol Beijing Peoples R China Colorado Sch Mines Dept Elect Engn & Comp Sci Golden CO 80401 USA

ISBN: (纸本)9781509053360

In this paper, we propose to leverage the emerging deep learning techniques for spatiotemporal modeling and prediction in cellular networks, based on big system data. First, we perform a preliminary analysis for a big dataset from China Mobile, and use traffic load as an example to show non-zero temporal autocorrelation and non-zero spatial correlation among neighboring Base Stations (BSs), which motivate us to discover both temporal and spatial dependencies in our study. Then we present a hybrid deep learning model for spatiotemporal prediction, which includes a novel autoencoder-based deep model for spatial modeling and Long Short-Term Memory units (LSTMs) for temporal modeling. The autoencoder-based model consists of a Global Stacked autoencoder (GSAE) and multiple Local SAEs (LSAEs), which can offer good representations for input data, reduced model size, and support for parallel and application-aware training. Moreover, we present a new algorithm for training the proposed spatial model. We conducted extensive experiments to evaluate the performance of the proposed model using the China Mobile dataset. The results show that the proposed deep model significantly improves prediction accuracy compared to two commonly used baseline methods, ARIMA and SVR. We also present some results to justify effectiveness of the autoencoder-based spatial model.

关键词： Cellular Network Big Data Spatiotemporal Modeling Deep Learning autoencoder Recurrent Neural Network

来源：评论

学校读者我要写书评

暂无评论

Speech Restoration Based on Deep Learning autoencoder with Layer-Wised Pretraining

Speech Restoration Based on Deep Learning Autoencoder with L...

引用

13th Annual Conference of the International-Speech-Communication-Association

作者： Lu, Xugang Matsuda, Shigeki Hori, Chiori Kashioka, Hideki Natl Inst Informat & Commun Technol Tokyo Japan

ISBN: (纸本)9781622767595

Neural network can be used to "remember" speech patterns by encoding speech statistical regularity in network parameters. Clean speech can be "recalled" when noisy speech is input to the network. Adding more hidden layers can increase network capacity. But when the hidden layer size increases (deep network), the network is easily to be trapped to a local solution when traditional training strategy is used. Therefore, the performance of using a deep network sometimes is even worse than using a shallow network. In this study, we explore the greedy layer-wised pretraining strategy to train a deep autoencoder (DAE) for speech restoration, and apply the restored speech for noisy robust speech recognition. The DAB is first pretrained using quasi-Newton optimization algorithm layer by layer in which each layer is regarded as a shallow autoencoder. And the output of the preceding layer is served as the input to the next layer. The pretrained layers are stacked and "unrolled" to be a DAB. The pretrained parameters are served as initial parameters of the DAB which are used to refine training. The trained DAB is used as a filter for speech restoration when noisy speech is given. Noisy robust speech recognition experiments were done to examine the performance of the trained deep network. Experimental results show that the DAB trained with pretraining process significantly improved the performance of speech restoration from noisy input.

关键词： Deep learning autoencoder noise reduction speech recognition

来源：评论

学校读者我要写书评

暂无评论

Software Lifecycle Management Unsupervised Anomaly Detection

Software Lifecycle Management Unsupervised Anomaly Detection

引用

作者： Ludwig Friborg Victor Christoffersson Chalmers Tekniska Hogskola

学位级别：硕士

The purpose of this thesis is to evaluate if unsupervised anomaly detection, the task of finding anomalies in unlabelled data, can be used as a supportive tool for software life cycle management in finding errors which are tedious to detect manually. The goal is to apply the techniques of unsupervised machine learning on data-sets that are collected and analysed from a miniature-scaled research vehicle system that resembles the operation of a real automotive vehicles electrical architecture. Using a stacked autoencoder implemented with TensorFlow, the final application is able to detect anomalies within the collected data-sets from the research vehicle. This proves the concept of utilising machine learning for error detection as a viable method. Finally concluding whether the techniques of unsupervised anomaly detection is applicable on a larger scale for real automotive vehicles.

关键词： Machine learning Unspervised Anomaly Detection autoencoder Software Life-cycle Management Artificial Nural 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425页 << < 409 410 411 412 413 414 415 416 417 418 > >>

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：