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

128 篇 会议
3 篇 期刊文献
2 册 图书

馆藏范围

133 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

115 篇 工学
- 104 篇 计算机科学与技术...
- 29 篇 软件工程
- 13 篇 电气工程
- 11 篇 信息与通信工程
- 9 篇 生物医学工程（可授...
- 9 篇 生物工程
- 6 篇 光学工程
- 4 篇 控制科学与工程
- 3 篇 交通运输工程
- 2 篇 仪器科学与技术
- 1 篇 材料科学与工程（可...
- 1 篇 动力工程及工程热...
- 1 篇 建筑学
- 1 篇 化学工程与技术
- 1 篇 石油与天然气工程
35 篇 理学
- 16 篇 数学
- 16 篇 生物学
- 8 篇 物理学
- 7 篇 统计学（可授理学、...
- 1 篇 化学
- 1 篇 系统科学
14 篇 医学
- 13 篇 临床医学
- 5 篇 基础医学(可授医学...
- 4 篇 药学(可授医学、理...
- 1 篇 公共卫生与预防医...
- 1 篇 特种医学
10 篇 管理学
- 6 篇 图书情报与档案管...
- 4 篇 管理科学与工程(可...
- 2 篇 工商管理
2 篇 农学
- 2 篇 作物学

主题

21 篇 neural networks
7 篇 artificial neura...
6 篇 pattern recognit...
5 篇 neurons
5 篇 artificial intel...
4 篇 deep learning
4 篇 deep neural netw...
4 篇 artificial neura...
4 篇 training
3 篇 face recognition
3 篇 feature extracti...
3 篇 recurrent neural...
2 篇 mixture modeling
2 篇 training data
2 篇 image segmentati...
2 篇 convolution
2 篇 semisupervised l...
2 篇 computed tomogra...
2 篇 independent comp...
2 篇 predictive model...

机构

8 篇 univ ulm inst ne...
5 篇 univ ulm dept ne...
2 篇 tech univ claust...
2 篇 univ jaume 1 dep...
2 篇 univ hosp ulm de...
2 篇 univ siena dipar...
2 篇 univ siena diism...
2 篇 univ sherbrooke ...
2 篇 univ leipzig ins...
1 篇 medical imaging ...
1 篇 dipartimento di ...
1 篇 national institu...
1 篇 department of bi...
1 篇 nanyang technol ...
1 篇 univ sao paulo i...
1 篇 tech univ claust...
1 篇 gene expression ...
1 篇 natl tsing hua u...
1 篇 ipk gatersleben ...
1 篇 university of no...

作者

13 篇 schwenker friedh...
7 篇 palm guenther
5 篇 kestler hans a.
4 篇 hernandez-espino...
4 篇 fernandez-redond...
4 篇 torres-sospedra ...
3 篇 trentin edmondo
3 篇 hammer barbara
3 篇 bianchini monica
2 篇 granger eric
2 篇 sarti lorenzo
2 篇 villmann thomas
2 篇 maggini marco
2 篇 ziou d
2 篇 lin feng
2 篇 windeatt terry
2 篇 fausser stefan
2 篇 piantadosi gabri...
2 篇 hasenfuss alexan...
2 篇 seiffert udo

语言

132 篇 英文
1 篇 中文

检索条件"任意字段=2nd IAPR Workshop on Artificial Neural Networks in Pattern Recognition"

共 133 条记录，以下是71-80 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：

Probabilistic models based on the Π-sigmoid distribution

引用

3rd iapr workshop on artificial neural networks in pattern recognition

作者： Alivanoglou, Anastasios Likas, Aristidis Univ Ioannina Dept Comp Sci GR-45110 Ioannina Greece

ISBN: (纸本)9783540699385

Mixture models constitute a popular type of probabilistic neural networks which model the density of a dataset using a convex combination of statistical distributions, with the Gaussian distribution being the one most commonly used. In this work we propose a new probability density function, called the II-sigmoid, from its ability to form the shape of the letter "II" by appropriately combining two sigmoid functions. We demonstrate its modeling properties and the different shapes that can take for particular values of its parameters. We then present the II-sigmoid mixture model and propose a maximum likelihood estimation method to estimate the parameters of such a mixture model using the Generalized Expectation Maximization algorithm. We assess the performance of the proposed method using synthetic datasets and also on image segmentation and illustrate its superiority over Gaussian mixture models.

关键词： probabilistic neural networks mixture models Pi-sigmoid distribution orthogonal clustering image segmentation

来源：评论

学校读者我要写书评

暂无评论

artificial neural network based automatic face model generation system from only one fingerprint

引用

3rd iapr workshop on artificial neural networks in pattern recognition

作者： Sagiroglu, Seref Ozkaya, Necla Gazi Univ Engn & Architecture Fac Dept Comp Engn TR-06570 Ankara Turkey Erciyes Univ Fac Engn Dept Comp Engn TR-38039 Kayseri Turkey

ISBN: (纸本)9783540699385

Biometrics technology has received increasingly more attention during the last three decades. Since the performance of biometric systems has reached a satisfactory level for applications, a number of biometric features have been deeply studied, tested and successfully deployed in applications. Relationships among biometric features have not been studied so far. This study focuses on analysing the existence of any relationships among fingerprints and faces. For doing that an intelligent system based on artificial neural networks for generating face models including eyes, nose, mouth, ears and face border from only one fingerprint with the errors among 2.0-12.9% was developed. Experimental results have shown that there are close realitionships among fingerprints and faces and it is possible to generate faces from only one fingerprint image without knowing any information about faces. Although the proposed system is an initial study and it is still under development, the results are very encouraging and promising for the future developments and applications.

关键词： biometrics artificial neural network intelligent systems fingerprint identification face recognition

来源：评论

学校读者我要写书评

暂无评论

Texture classification with Generalized Fourier Descriptors in dimensionality reduction context: An overview exploration

引用

3rd iapr workshop on artificial neural networks in pattern recognition

作者： Journaux, Ludovic Destain, Marie-France Miteran, Johel Piron, Alexis Cointault, Frederic Fac Univ Sci Agronom Gembloux Unite Mecan & Construct Passage Deportes 2 B-5030 Gembloux Belgium Univ Bourgogne Lab. Le2i F-21078 Dijon France ENESAD UP GAP F-21079 Dijon France

ISBN: (纸本)9783540699385

In the context of texture classification, this article explores the capacity and the performance of some combinations of feature extraction, linear and nonlinear dimensionality reduction techniques and several kinds of classification methods. The performances are evaluated and, compared in term of classification error. in order to test our texture classification protocol, the experiment carried out images from two different sources, the well known Brodatz database and our leaf texture images database.

关键词： texture classification motion descriptors dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

A bio-inspired neural model for colour image segmentation

引用

3rd iapr workshop on artificial neural networks in pattern recognition

作者： Diaz-Pernas, Francisco Javier Anton-Rodriguez, Miriam Diez-Higuera, Jose Fernando Martinez-Zarzuela, Mario Univ Valladolid Telecommun Engn Sch Dept Signal Theory Commun & Telemat Engn Valladolid Spain

ISBN: (纸本)9783540699385

This paper describes a multi-scale neural model to enhance regions and extract contours of colour-texture image taking into consideration the theory for visual information processing in the early stages of human visual system. It is composed of two main components: the Colour Opponent System (COS) and the Chromatic Segmentation System (CSS). The structure of the CSS architecture is based on BCS/FCS systems, so the proposed architecture maintains the essential qualities of the base model such as illusory contours extraction, perceptual grouping and discounting the illuminant. Experiments performed show the good visual results obtained and the robustness of the model when processing images presenting different levels of noise.

关键词： image analysis image segmentation neural network multiple scale model Boundary Contour System Feature Contour System enhancing colour image regions colour-opponent processes

来源：评论

学校读者我要写书评

暂无评论

Cyclostationary neural networks for air pollutant concentration prediction

引用

3rd iapr workshop on artificial neural networks in pattern recognition

作者： Bianchini, Monica Di Iorio, Ernesto Maggini, Marco Pucci, Augusto Dipartimento Ingn Informaz I-53100 Siena Italy

ISBN: (纸本)9783540699385

There are many substances in the air which may impair the health of plants and animals, including humans, that arise both from natural processes and human activity. Nitrogen dioxide N02 and particulate matter (PM10, PM2.5) emissions constitute a major concern in urban areas pollution. The state of the air is, in fact, an important factor in the quality of life in the cities, since it affects the health of the community and directly influences the sustainability of our lifestyles and production methods. In this paper we propose a cyclostationary neural network (CNN) model for the prediction of the N02 and PM,o concentrations. The cyclostationary nature of the problem guides the construction of the CNN architecture, which is composed by a number of MLP blocks equal to the cyclostationary period in the analyzed phenomenon, and is independent from exogenous inputs. Some experiments are also reported in order to show how the CNN model significantly outperforms standard statistical tools and linear regressors usually employed in these tasks.

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

How robust is a probabilistic neural VLSI system against environmental noise

引用

3rd iapr workshop on artificial neural networks in pattern recognition

作者： Lu, C. C. Li, C. C. Chen, H. Natl Tsing Hua Univ Dept Elect Engn Hsinchu 30013 Taiwan

ISBN: (纸本)9783540699385

Implementing probabilistic models in the Very-Large-ScaleIntegration (VLSI) has been attractive to implantable biomedical devices for improving sensor fusion and power management. However, implantable devices are, normally exposed to noisy environments which can introduce non-negligible computational errors and hinder optimal modelling on-chip. While the probablistic model called the Continuous Restricted Boltzmann Machine (CRBM) has been shown useful and realised as a VLSI system with noise-induced stochastic behaviour, this paper investigates the suggestion that the stochastic behaviour in VLSI could enhance the tolerance against the interferences of environmental noise. The behavioural simulation of the CRBM system is used to examine the system's performance in the presence of environmental noise. Furthermore, the possibility of using environmental noise to induce stochasticity in VLSI for computation is investigated.

关键词： VLSI circuits

来源：评论

学校读者我要写书评

暂无评论

Combining methods for dynamic multiple classifier systems

引用

3rd iapr workshop on artificial neural networks in pattern recognition

作者： Tomas, Amber Univ Oxford Dept Stat Oxford OX2 3TG England

ISBN: (纸本)9783540699385

Most of what we know about multiple classifier systems is based on empirical findings, rather than theoretical results. Although there exist some theoretical results for simple and weighted averaging, it is difficult to gain an intuitive feel for classifier combination. In this paper we derive a bound on the region of the feature space in which the decision boundary can lie, for several methods of classifier combination using non-negative weights. This includes simple and weighted averaging of classifier outputs, and allows for a more intuitive understanding of the influence of the classifiers combined. We then apply this result to the design of a multiple logistic model for classifier combination in dynamic scenarios, and discuss its relevance to the concept of diversity amongst a set of classifiers. We consider the use of pairs of classifiers trained on label-swapped data, and deduce that although non-negative weights may be beneficial in stationary classification scenarios, for dynamic problems it is often necessary to use unconstrained weights for the combination.

关键词： dynamic classification multiple classifier systems classifier diversity

来源：评论

学校读者我要写书评

暂无评论

Supervised incremental learning with the fuzzy ARTMAP neural network

引用

3rd iapr workshop on artificial neural networks in pattern recognition

作者： Connolly, Jean-Francois Granger, Eric Sabourin, Robert Ecole Technol Super Dept Genie Prod Automatisee Lab Imagerie Vis & Intelligence Artificielle Montreal PQ H3C 1K3 Canada

ISBN: (纸本)9783540699385

Automatic pattern classifiers that allow for on-line incremental learning can adapt internal class models efficiently in response to new information without retraining from the start using all training data and without being subject to catastrophic forgeting. In this paper, the performance of the fuzzy ARTMAP neural network for supervised incremental learning is compared to that of supervised batch learning. An experimental protocole is presented to assess this network's potential for incremental learning of new blocks of training data, in terms of generalization error and resource requirements, using several synthetic pattern recognition problems. The advantages and drawbacks of training fuzzy ARTMAP incrementally are assessed for different data block sizes and data set structures. Overall results indicate that error rate of fuzzy ARTMAP is significantly higher when it is trained through incremental learning than through batch learning. As the size of training blocs decreases, the error rate acheived through incremental learning grows, but provides a more compact network using fewer training epochs. In the cases where the class distributions overlap, incremental learning shows signs of over-training. With a growing numbers of training patterns, the error rate grows while the compression reaches a plateau.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Patch relational neural gas - Clustering of huge dissimilarity datasets

引用

3rd iapr workshop on artificial neural networks in pattern recognition

作者： Hasenfuss, Alexander Hammer, Barbara Rossi, Fabrice Tech Univ Clausthal Dept Informat Clausthal Zellerfeld Germany INRIA Rocquencourt Projet AxIS Domaine Voluceau Rocquencourt BP 105 F-78513 Le Chesnay France

ISBN: (纸本)9783540699385

Clustering constitutes an ubiquitous problem when dealing with huge data sets for data compression, visualization, or preprocessing. Prototype-based neural methods such as neural gas or the self-organizing map offer an intuitive and fast variant which represents data by means of typical representatives, thereby running in linear time. Recently, an extension of these methods towards relational clustering has been proposed which can handle general non-vectorial data characterized by dissimilarities only, such as alignment or general kernels. This extension, relational neural gas, is directly applicable in important domains such as bioinformatics or text clustering. However, it is quadratic in m both in memory and in time (m being the number of data points). Hence, it is infeasible for huge data sets. In this contribution we introduce an approximate patch version of relational neural gas which relies on the same cost function but it dramatically reduces time and memory requirements. It offers a single pass clustering algorithm for huge data sets, running in constant space and linear time only.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

Boosting threshold classifiers for high-dimensional data in functional genomics

引用

3rd iapr workshop on artificial neural networks in pattern recognition

作者： Lausser, Ludwig Buchholz, Malte Kestler, Hans A. Univ Hosp Ulm Dept Internal Med Ulm Germany Univ Ulm Inst Neural Informat Processing Ulm Germany Univ Hosp Marburg SP Gastroenterol Internal Med Marburg Germany

ISBN: (纸本)9783540699385

Diagnosis of disease based on the classification of DNA microarray gene expression profiles of clinical samples is a promising novel approach to improve the performance and accuracy of current routine diagnostic procedures. In many applications ensembles outperform single classifiers. In a clinical setting a combination of simple classification rules, such as single threshold classifiers on individual gene expression values, may provide valuable insights and facilitate the diagnostic process. A boosting algorithm can be used for building such decision rules by utilizing single threshold classifiers as base classifiers. AdaBoost can be seen as the predecessor of many boosting algorithms developed, unfortunately its performance degrades on high-dimensional data. Here we compare extensions of AdaBoost namely MultiBoost, MadaBoost and AdaBoost-VC in cross-validation experiments on noisy high-dimensional artifical and real data sets. The artifical data sets are so constructed, that features, which are relevant for the class distinction, can easily be read out. Our special interest is in the features the ensembles select for classification and how many of them are effectively related to the original class distinction.

关键词： Adaptive boosting

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14页 << < 4 5 6 7 8 9 10 11 12 13 > >>

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：