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

68 篇 会议
13 篇 期刊文献

馆藏范围

81 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

76 篇 工学
- 74 篇 计算机科学与技术...
- 13 篇 软件工程
- 5 篇 信息与通信工程
- 4 篇 生物工程
- 2 篇 化学工程与技术
- 2 篇 生物医学工程（可授...
- 1 篇 电气工程
- 1 篇 电子科学与技术（可...
- 1 篇 控制科学与工程
- 1 篇 土木工程
16 篇 理学
- 11 篇 数学
- 8 篇 生物学
- 3 篇 系统科学
- 2 篇 物理学
- 2 篇 化学
- 1 篇 地球物理学
- 1 篇 地质学
- 1 篇 统计学（可授理学、...
6 篇 管理学
- 5 篇 图书情报与档案管...
- 1 篇 管理科学与工程(可...
3 篇 法学
- 3 篇 社会学
2 篇 医学
- 2 篇 基础医学(可授医学...
- 2 篇 临床医学
- 2 篇 药学(可授医学、理...

主题

5 篇 supervised learn...
4 篇 recursive neural...
3 篇 deep learning
3 篇 neural networks
3 篇 face recognition
3 篇 pattern recognit...
3 篇 feature extracti...
2 篇 vision transform...
2 篇 multi-label clas...
2 篇 mixture modeling
2 篇 weighting of dat...
2 篇 semiconductor ma...
2 篇 pattern classifi...
2 篇 human computer i...
2 篇 graph edit dista...
2 篇 feed-forward neu...
2 篇 polynomial appro...
2 篇 class imbalance
2 篇 learning prefere...
2 篇 time series fore...

机构

5 篇 concordia univ d...
4 篇 univ ulm inst ne...
3 篇 univ jaume 1 dep...
2 篇 univ london birk...
2 篇 institute of neu...
2 篇 multimedia univ ...
2 篇 institute for in...
2 篇 helsinki univ te...
2 篇 institute of neu...
2 篇 univ paris 06 la...
2 篇 univ hosp ulm de...
2 篇 ctr pattern regc...
2 篇 concordia univ d...
2 篇 univ toulouse 3 ...
2 篇 univ patras upai...
2 篇 univ ulm dept ne...
2 篇 institute of com...
2 篇 univ catholique ...
2 篇 univ siena dipar...
2 篇 ucl dept comp sc...

作者

12 篇 schwenker friedh...
5 篇 trentin edmondo
5 篇 hernandez-espino...
5 篇 fernandez-redond...
5 篇 torres-sospedra ...
4 篇 riesen kaspar
4 篇 palm guenther
4 篇 kestler hans a.
3 篇 krzyzak adam
3 篇 scherer stefan
2 篇 granger eric
2 篇 piccinini f
2 篇 pudil p
2 篇 frasconi p
2 篇 ziou d
2 篇 simon g
2 篇 inesta jm
2 篇 krzyzak a
2 篇 brown m
2 篇 michel-sendis c

语言

81 篇 英文

检索条件"任意字段=1st IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition"

共 81 条记录，以下是31-40 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：

Partially Supervised Learning - First iapr tc3 workshop, PSL 2011, Revised Selected Papers

Partially Supervised Learning - First IAPR TC3 Workshop, PSL...

引用

1st iapr-tc3 workshop on Partially Supervised Learning, PSL 2011

ISBN: (纸本)9783642282577

The proceedings contain 17 papers. The topics discussed include: unlabeled data and multiple views;studying self- and active-training methods for multi-feature set emotion recognition;semi-supervised linear discriminant analysis using moment constraints;manifold-regularized minimax probability machine;supervised and unsupervised co-training of adaptive activation functions in neural nets;semi-unsupervised weighted maximum-likelihood estimation of joint densities for the co-training of adaptive activation functions;semi-supervised kernel clustering with sample-to-cluster weights;homeokinetic reinforcement learning;iterative refinement of hmm and HCRF for sequence classification;on the utility of partially labeled data for classification of microarray data;multi-instance methods for partially supervised image segmentation;and semi-supervised training set adaption to unknown countries for traffic sign classifiers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Social coordination assessment: Distinguishing between shape and timing

Social coordination assessment: Distinguishing between shape...

引用

1st iapr tc3 workshop on Multimodal pattern recognition of Social Signals in Human-Computer-Interaction, MPRSS 2012

作者： Delaherche, Emilie Boucenna, Sofiane Karp, Koby Michelet, stéphane Achard, Catherine Chetouani, Mohamed Institute of Intelligent Systems and Robotics University Pierre and Marie Curie 75005 Paris France

ISBN: (纸本)9783642370809

In this paper, we propose a new framework to assess temporal coordination (synchrony) and content coordination (behavior matching) in dyadic interaction. The synchrony module is dedicated to identify the time lag and possible rhythm between partners. The imitation module aims at assessing the distance between two gestures, based on 1-Class SVM models. These measures discriminate significantly conditions where synchrony or behavior matching occurs from conditions where these phenomenons are absent. Moreover, these measures are unsupervised and could be implemented online. © 2013 Springer-Verlag.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Comparison of combined probabilistic connectionist models in a forensic application

Comparison of combined probabilistic connectionist models in...

引用

1st iapr-tc3 workshop on Partially Supervised Learning, PSL 2011

作者： Trentin, Edmondo Lusnig, Luca Cavalli, Fabio Dip. di Ingegneria dell'Informazione Università di Siena Italy Research Unit of Paleoradiology and All. Sci. AOUTS Trieste Italy

ISBN: (纸本)9783642282577

A growing interest toward automatic, computer-based tools has been spreading among forensic scientists and anthropologists wishing to extend the armamentarium of traditional statistical analysis and classification techniques. The combination of multiple paradigms is often required in order to fit the difficult, real-world scenarios involved in the area. The paper presents a comparison of combination techniques that exploit neural networks having a probabilistic interpretation within a Bayesian framework, either as models of class-posterior probabilities or as class-conditional density functions. Experiments are reported on a severe sex determination task relying on 1400 scout-view CT-scan images of human crania. It is shown that connectionist probability estimates yield higher accuracies than traditional statistical algorithms. Furthermore, the performance benefits from proper mixtures of neural models, and it turns up affected by the specific combination technique adopted. © 2012 Springer-Verlag.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Decision fusion on boosting ensembles

引用

3rd iapr workshop on artificial neural networks in pattern recognition

作者： Torres-Sospedra, Joaquin Hernandez-Espinosa, Carlos Fernandez-Redondo, Mercedes Univ Jaume 1 Dept Ingn & Ciencia Computadores Castellon de La Plana Spain

ISBN: (纸本)9783540699385

Training an ensemble of neural networks is an interesting way to build a Multi-net System. One of the key factors to design an ensemble is how to combine the networks to give a single output. Although there are some important methods to build ensembles, Boosting is one of the most important ones. Most of methods based on Boosting use an specific combiner (Boosting Combiner). Although the Boosting combiner provides good results on boosting ensembles, the results of previouses papers show that the simple combiner Output Average can work better than the Boosting combiner. In this paper, we study the performance of sixteen different combination methods for ensembles previously trained with Adaptive Boosting and Average Boosting. The results show that the accuracy of the ensembles trained with these original boosting methods can be improved by using the appropriate alternative combiner.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Researching on Multi-Net systems based on stacked Generalization

引用

3rd iapr workshop on artificial neural networks in pattern recognition

作者： Hernandez-Espinosa, Carlos Torres-Sospedra, Joaquin Fernandez-Redondo, Mercedes Univ Jaume 1 Dept Ingn & Ciencia Computadores Castellon de La Plana Spain

ISBN: (纸本)9783540699385

Among the approaches to build a Multi-Net system, stacked Generalization is a well-known model. The classification system is divided into two steps. Firstly, the level-O generalizers are built using the original input data and the class label. Secondly, the level-] generalizers networks are built using the outputs of the level-O generalizers and the class label. Then, the model is ready for pattern recognition. We have found two important adaptations of stacked Generalization that can be applyied to artificial neural networks. Moreover, two combination methods, stacked and stacked+, based on the stacked Generalization idea were successfully introduced by our research group. In this paper, we want to empirically compare the version of the original stacked Generalization along with other traditional methodologies to build Multi-Net systems. Moreover, we have also compared the combiners we proposed. The best results are provided by the combiners stacked and stacked+ when they are applied to ensembles previously trained with Simple Ensemble.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Fusion of fragmentary classifier decisions for affective state recognition

Fusion of fragmentary classifier decisions for affective sta...

引用

1st iapr tc3 workshop on Multimodal pattern recognition of Social Signals in Human-Computer-Interaction, MPRSS 2012

作者： Krell, Gerald Glodek, Michael Panning, Axel Siegert, Ingo Michaelis, Bernd Wendemuth, Andreas Schwenker, Friedhelm Institute for Electronics Signal Processing and Communications Otto-von-Guericke University Magdeburg Germany Institute of Neural Information Processing Ulm University Germany

ISBN: (纸本)9783642370809

Real human-computer interaction systems based on different modalities face the problem that not all information channels are always available at regular time steps. Nevertheless an estimation of the current user state is required at anytime to enable the system to interact instantaneously based on the available modalities. A novel approach to decision fusion of fragmentary classifications is therefore proposed and empirically evaluated for audio and video signals of a corpus of non-acted user behavior. It is shown that visual and prosodic analysis successfully complement each other leading to an outstanding performance of the fusion architecture. © 2013 Springer-Verlag.

关键词： Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

studying self- and active-training methods for multi-feature set emotion recognition

Studying self- and active-training methods for multi-feature...

引用

1st iapr-tc3 workshop on Partially Supervised Learning, PSL 2011

作者： Esparza, José Scherer, stefan Schwenker, Friedhelm Institute of Neural Information Processing University of Ulm Germany School of Linguistic Speech and Communication Sciences Trinity College Dublin Ireland

ISBN: (纸本)9783642282577

Automatic emotion classification is a task that has been subject of study from very different approaches. Previous research proves that similar performance to humans can be achieved by adequate combination of modalities and features. Nevertheless, large amounts of training data seem necessary to reach a similar level of accurate automatic classification. The labelling of training, validation and test sets is generally a difficult and time consuming task that restricts the experiments. Therefore, in this work we aim at studying self and active training methods and their performance in the task of emotion classification from speech data to reduce annotation costs. The results are compared, using confusion matrices, with the human perception capabilities and supervised training experiments, yielding similar accuracies. © 2012 Springer-Verlag.

关键词： Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

A Refinement Algorithm for Deep Learning via Error-Driven Propagation of Target Outputs 8th

A Refinement Algorithm for Deep Learning via Error-Driven Pr...

引用

8th iapr tc3 workshop on artificial neural networks in pattern recognition (ANNPR)

作者： Laveglia, Vincenzo Trentin, Edmondo Univ Firenze DINFO Via S Marta 3 I-50139 Florence Italy Univ Siena DIISM Via Roma 56 I-53100 Siena Italy

ISBN: (纸本)9783319999784;9783319999777

Target propagation in deep neural networks aims at improving the learning process by determining target outputs for the hidden layers of the network. To date, this has been accomplished via gradient-descent or relying on autoassociative networks applied top-to-bottom in order to synthesize targets at any given layer from the targets available at the adjacent upper layer. This paper proposes a different, error-driven approach, where a regular feed-forward neural net is trained to estimate the relation between the targets at layer l and those at layer l - 1 given the error observed at layer l. The resulting algorithm is then combined with a pre-training phase based on backpropagation, realizing a proficuous "refinement" strategy. Results on the MNIst database validate the feasibility of the approach.

关键词： Target propagation Deep learning Deep neural network Refinement learning

来源：评论

学校读者我要写书评

暂无评论

A non-invasive multi-sensor capturing system for human physiological and behavioral responses analysis

A non-invasive multi-sensor capturing system for human physi...

引用

1st iapr tc3 workshop on Multimodal pattern recognition of Social Signals in Human-Computer-Interaction, MPRSS 2012

作者： Polikovsky, Senya Quiros-Ramirez, Maria Alejandra Onisawa, Takehisa Kameda, Yoshinari Ohta, Yuichi Graduate School of System and Information Engineering University of Tsukuba 1-1-1 Tennodai Tsukuba 305-8573 Japan

ISBN: (纸本)9783642370809

We present a new noninvasive multi-sensor capturing system for recording video, sound and motion data. The characteristic of the system is its 1msec. order accuracy hardware level synchronization among all the sensors as well as automatic extraction of variety of ground truth from the data. The proposed system enables the analysis of the correlation between variety of psychophysiological model (modalities), such as facial expression, body temperature changes, gaze analysis etc... . Following benchmarks driven framework principles, the data captured by our system is used to establish benchmarks for evaluation of the algorithms involved in the automatic emotions recognition process. © 2013 Springer-Verlag.

关键词： Physiology

来源：评论

学校读者我要写书评

暂无评论

Bayesian Learning of Generalized Gaussian Mixture Models on Biomedical Images

Bayesian Learning of Generalized Gaussian Mixture Models on ...

引用

4th workshop on artificial neural networks in pattern recognition

作者： Elguebaly, Tarek Bouguila, Nizar Concordia Univ Fac Engn & Comp Sci CIISE Montreal PQ H3G 2W1 Canada

ISBN: (纸本)9783642121586

In the context of biomedical image processing and bioinformatics, an important problem is the development of accurate models for image segmentation and DNA spot detection. In this paper we propose a highly efficient unsupervised Bayesian algorithm for biomedical image segmentation and spot detection of cDNA microarray images, based on generalized Gaussian mixture models. Our work is motivated by the fact that biomedical and cDNA microarray images both contain non-Gaussian characteristics, impossible to model using rigid distributions like the Gaussian. Generalized Gaussian mixture models are robust in the presence of noise and outliers and are more flexible to adapt the shape of data.

关键词： Bioinformatics

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9页 << < 1 2 3 4 5 6 7 8 9 > >>

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：