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

248 篇 会议
18 篇 期刊文献
3 册 图书

馆藏范围

269 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

231 篇 工学
- 217 篇 计算机科学与技术...
- 53 篇 软件工程
- 32 篇 信息与通信工程
- 15 篇 生物工程
- 13 篇 电气工程
- 10 篇 生物医学工程（可授...
- 6 篇 光学工程
- 4 篇 控制科学与工程
- 4 篇 化学工程与技术
- 3 篇 机械工程
- 3 篇 材料科学与工程（可...
- 3 篇 建筑学
- 2 篇 土木工程
- 1 篇 仪器科学与技术
- 1 篇 电子科学与技术（可...
- 1 篇 石油与天然气工程
63 篇 理学
- 37 篇 数学
- 21 篇 生物学
- 15 篇 物理学
- 8 篇 统计学（可授理学、...
- 3 篇 化学
- 2 篇 系统科学
24 篇 管理学
- 20 篇 图书情报与档案管...
- 4 篇 管理科学与工程(可...
- 3 篇 工商管理
11 篇 医学
- 10 篇 临床医学
- 3 篇 基础医学(可授医学...
- 3 篇 药学(可授医学、理...
4 篇 法学
- 4 篇 社会学
1 篇 经济学
- 1 篇 应用经济学
1 篇 农学

主题

22 篇 neural networks
15 篇 pattern recognit...
14 篇 deep learning
11 篇 convolutional ne...
7 篇 face recognition
7 篇 feature extracti...
7 篇 supervised learn...
7 篇 recurrent neural...
5 篇 deep neural netw...
5 篇 recurrent neural...
5 篇 emotion recognit...
5 篇 artificial intel...
4 篇 neurons
4 篇 support vector m...
4 篇 human computer i...
4 篇 image segmentati...
4 篇 graph neural net...
4 篇 density estimati...
4 篇 recursive neural...
4 篇 character recogn...

机构

11 篇 univ ulm inst ne...
5 篇 concordia univ d...
5 篇 univ ulm dept ne...
4 篇 institute of neu...
4 篇 ulm univ inst ne...
4 篇 univ siena dipar...
3 篇 concordia univ d...
3 篇 univ siena dipar...
2 篇 univ london birk...
2 篇 tech univ claust...
2 篇 univ jaume 1 dep...
2 篇 univ siena siena
2 篇 institute of neu...
2 篇 institute for in...
2 篇 helsinki univ te...
2 篇 univ paris 06 la...
2 篇 ulm university i...
2 篇 heriot watt univ...
2 篇 univ ulm inst ne...
2 篇 univ hosp ulm de...

作者

41 篇 schwenker friedh...
12 篇 trentin edmondo
10 篇 palm guenther
8 篇 kestler hans a.
8 篇 meudt sascha
6 篇 el gayar neamat
6 篇 riesen kaspar
6 篇 thiam patrick
5 篇 stadelmann thilo
5 篇 kaechele markus
5 篇 amirian mohammad...
4 篇 burnaev evgeny
4 篇 hernandez-espino...
4 篇 hammer barbara
4 篇 lausser ludwig
4 篇 bianchini monica
4 篇 fernandez-redond...
4 篇 torres-sospedra ...
4 篇 fischer andreas
4 篇 palm günther

语言

268 篇 英文
1 篇 中文

检索条件"任意字段=3rd IAPR Workshop on Artificial Neural Networks in Pattern Recognition"

共 269 条记录，以下是251-260 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：

Character recognition with neural assemblies 3rd

引用

3rd International workshop on artificial neural networks, IWANN 1995

作者： Vico, Francisco J. Ortega, F. Almaraz, J. Sandoval, F. E.T.S.I. de Telecomunicaciòn Dpto. Tecnologfa Electrìnica Dpto. Psicobiologfa Universidad de Màlaga Plaza E1 Ejido s/n Màlaga29013 Spain

ISBN: (纸本)3540594973

In living beings, any pattern recognition task involves complex processes of concepts formation. We propose a model based on the principle of neural assemblies to develop internal representations of characters. neural assemblies self-organize themselves by extracting the relevant information of the characters set depending on the previously stored characters. The principal consequences of this are that less storage capacity is needed, and it makes easer the clasiffication with a delta rule. Examples of this task are exposed, where it can be seen the way in which the assemblies store the characters, and how the classification of the internal representations is performed. © 1995, Springer Verlag. All rights reserved.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Quasi-optimum combination of multilayer perceptrons for adaptive multiclass pattern recognition 3rd

引用

3rd International workshop on artificial neural networks, IWANN 1995

作者： García, Alberto Ruiz Areas Túnez, Francisco J. Departamento de Informática y Sistemas Universidad de Murcia Spain

ISBN: (纸本)3540594973

Standard multiclass pattern recognition requires frequent re-learning stages when the set of categories of interest evolves in time. In order to minimize the computation costs of class incorporation and removal, we divide the global multiclass recognizer into a collection of class pairwise neural dichotomizers. When a new class appears, an adequate set of dichotomizers is created and trained to discriminate the new class from the rest. If a class disappears, its associated diehotomizers are eliminated In both cases previously learned knowledge is not disturbed. The properties of neural recognizers and pairwise modularization allow an analytic quasi-optimum method for combining network outputs to obtain the global multiclass response. An incremental and distributed pattern recognition architecture is presented and its performance experimentally evaluated, obtaining better error rates and learning times than conventional multiclass recognizers using similar resources. The design is highly parallel and asyncronous, adequate for dynamic real time applications. © 1995, Springer Verlag. All rights reserved.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

A neural architecture for preattentive segmentation of sewage pipes video images 3rd

引用

3rd International workshop on artificial neural networks, IWANN 1995

作者： Ruiz-Del-Solar, Javier Köppen, Mario Fraunhofer-Institut IPK Berlin Department of Pattern Recognition Pascalstr. 8-9 Berlin10587 Germany

ISBN: (纸本)3540594973

This article describes a neural architecture for real time preattentive segmentation of sewage pipes video images, whose mechanisms are based on the mammalian early visual system. The architecture corresponds to a modified and simplified version of the Boundary contour System tuned to take advantage of the circular symmetric characteristics of the pipes images. Remarkable aspects of the proposed architecture are the application of a spatial complex logarithmic mapping stage, and the use of cooperative receptive fields with noncollinear branches. © 1995, Springer Verlag. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A neuro-money recognition using optimized Masks by GA 3rd

A neuro-money recognition using optimized Masks by GA

引用

3rd World Wisepersons workshop on Fuzzy Logic and neural networks/Genetic Algorithms, WWW 1994

作者： Takeda, Fumiaki Omatu, Sigeru GLORY LTD. Development Center 3-1 Shimoteno 1-Chome Himeji670 Japan University of Osaka Prefecture College of Engineering Department of Computer and systems sciences Gakuen Cho 1-1 SakaiOsaka593 Japan

ISBN: (纸本)9783540606079

Up to now, much research of the application to neural networks (NN) has been reported. We have proposed a neuro-pattern recognition for bill money with masks and have reported its effectiveness for money recognition. Recently, genetic algorithm (GA) is reported as the effective optimizing method. In this paper, we adopt the GA to mask optimization in the recognition method. Namely, we regard the position of the masked part in the input image as a gene. We operate crossover, selection, and mutation to some genes. By repeating a series of these operations, we can get effective masks for paper currency recognition. We compare the ability of NN using the optimized masks by the GA with the one of NN using the random masks determined by random numbers. Then we show that the GA is effective to optimize masks for the method of neuro-pattem recognition with masks. Furthermore, we develop high-speed neuro-recognition board to realize the neuro-pattem recognition for paper currency in the commercial products. © Springer-Verlag Berlin Heidelberg 1995.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

International workshop on artificial neural networks, 1995

引用

3rd International workshop on artificial neural networks, IWANN 1995

ISBN: (纸本)3540594973

The proceedings contain 148 papers. The special focus in this conference is on Neuroscience, Computational Models of Neurons, Organization Principles and Learning. The topics include: Cooperative organization of connectivity patterns and receptive fields in the visual pathway;neurobiological inspiration for the architecture and functioning of cooperating neural networks;synaptic modulation based artificial neural networks;self-organization of cortical receptive fields and columnar structures in a hebb trained neural network;an analytical solution of the compartmental model for use in local learning in artificial neural networks;modeling retinal high and low contrast sensitivity filters;a computational model of periodic-pattern-selective cells;modeling and analysis of some neural mechanisms for the genesis and control of respiratory pattern;a neural network model for plasticity in adult striate cortex;nervous system as a closed neural network;local accumulation of persistent activity at synaptic level;high order Boltzmann machines with continuous units;an adaptive control model of a locomotion by the central pattern generator;an associative neural network to model the developing mammalian hippocampus;the implementation of propositional logic in random neural networks;the influence of the sigmoid function parameters on the speed of back propagation learning;general transient length upper bound for recurrent neural networks;analysis of pruning in back propagation networks for artificial and real world mapping problems and a new algorithm for implementing a recursive neural network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Global versus local heuristic terminal attractor 3rd

引用

3rd International workshop on artificial neural networks, IWANN 1995

作者： Marìn, F.J. Garcìa, F. Sandoval, F. Dpto. Arquitectura y Tecnologla de Computadores y Electrònica Universidad de Màlaga Plaza E1 Ejido s/n Màlaga29013 Spain Dpto. Tecnologìa Electrònica Universidad de Màlaga Plaza E1 Ejido s/n Màlaga29013 Spain

ISBN: (纸本)3540594973

The Heuristic Terminal Attractor (H.T.A) [2,3] is one of the most widely used algorithms for training feedforward neural networks. This algorithm ensures the completion of the learning process in finite time, as well as reaching the global minimum of the error function. The H.T.A. implementation introduces a local adaptive gain factor, in the way that it only affects the weights which belong to a given neuron. The weights actualization rule works with partial information from the weights vector, making the local algorithm slower in learning time. In this paper, we introduce the global gain strategy for H.T.A., which updates the matrix weights using all the weights of the network, instead of partial information of the matrix weights. This global strategy provides shorter learning times than the local one. A theoretical computational study is given to compare the viability of global versus local algorithm, for an only processor and in the case in which a processor is available for every neuron. The results are shown for the encode/decode problem and for the pattern recognition of the alphabetical capital letters. © 1995, Springer Verlag. All rights reserved.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An associative neural network to model the developing mammalian hippocampus 3rd

引用

3rd International workshop on artificial neural networks, IWANN 1995

作者： Pont, Maria Teresa Signes Sanchez-Andres, Juan Vicente Dept. Fisiología Inst. Neurociencias Universidad de Alicante Spain

ISBN: (纸本)3540594973

Electrophysiological recording of pyramidal hippocampal cells along early postnatal development shows a pattern of maturation consisting of a progressive reduction of the accommodation and increasing excitability. Electrophysiological, pharmacological, behavioural and lesion techniques permit to manipulate cellular, synaptic and connectivity properties in order to explain how cellular and synaptic mechanisms interact with the pattern of connectivity to give rise to a behaviorally important output pattern. These techniques, although powerful, have their limitations in that only some of the potentially important cellular or synaptic properties are amenable to experimentation. We propose a complementary approach using an associative network model based Hebbian laws, able to simulate the biological system, whose sequential output depends on the interference between a slow and a fast components. © 1995, Springer Verlag. All rights reserved.

关键词： Biological systems

来源：评论

学校读者我要写书评

暂无评论

An adaptive control model of a locomotion by the central pattern generator 3rd

引用

3rd International workshop on artificial neural networks, IWANN 1995

作者： Nishii, Jun Department of Mathematical Engineering and Information Physics University of Tokyo 7-3-1 Hongo Bunkyo-kuTokyo113 Japan

ISBN: (纸本)3540594973

Most of basic locomotor patterns of living bodies are controlled by central pattern generators (CPGs) which are collective neural oscillators. The CPG sends control signals to muscular systems, and the activity of the CPG is strongly affected by sensory signals from the body. Therefore, it can be said that locomotor patterns are generated by the interaction between the CPGs and the body movements. To control a physical system, such as a leg, by the CPG, it would be necessary to obtain an adequate intrinsic frequency of the CPG and interactions between the CPG and the physical system. In this article, we regard a physical system as a physical oscillator and propose a learning algorithm to acquire these parameters and apply the learning method to the control of a hopping robot. The proposed learning method does not need any information about the dynamics of the controlled physical system and requires only local informations like the Hebbian rule. © 1995, Springer Verlag. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Logistic networks with DNA-like encoding and interactions 3rd

引用

3rd International workshop on artificial neural networks, IWANN 1995

作者： Farhat, Nabil H. Hernandez, Emilio Del Moral University of Pennsylvania The Moore School of Electrical Engineering 200 South 33rd Street PhiladelphiaPA19104 United States

ISBN: (纸本)3540594973

We consider a logistic network consisting of a coupled population of externally driven logistic processing elements (LPEs) or "neurons" with quantized interactions between them. The interactions are modeled after the encoding of genetic information in molecular biology, i.e. as in DNA molecules in terms of four nucleotide bases. A unique and versatile scheme for generating complex spatiotemporal input patterns to drive the network, that could contain chaotic components, is employed to study the network's behavior. Both coherent (phase-locked) and incoherent input patterns can be generated. We find that DNA-like encoding of interactions causes quantization and clustering to appear in the activity of the network which we represent by limit-set-diagrams (LSDs). Clustering means gouping of processing elements into subpopulations with period-m orbits where m is constant for each cluster, but the values of m are different for different clusters. The clustering is found to characterize the particular input pattern being applied to the network, it changes gradually with gradual change in the input, and appears to persist even when the input pattern contains chaotic components. A swiking similarity of bifurcation diagrams of isolated driven LPEs and of the LSDs generated to the bar patterns observed in gel-electropheresis of oligonucleotides* and DNA fragments is observed. This could portend a useful link to molecular biology and serve as basis for introducing a molecular computing paradigm in neural networks. © 1995, Springer Verlag. All rights reserved.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

A practical view of suboptimal Bayesian classification with radial Gaussian kernels 3rd

引用

3rd International workshop on artificial neural networks, IWANN 1995

作者： Voz, Jean-Luc Verleysen, Michel Thissen, Philippe Legat, Jean-Didier Université catholique de Louvain Laboratoire de Microélectronique - DICE 3 Place du Levant Louvain-La-NeuveB-1348 Belgium

ISBN: (纸本)3540594973

For pattern classification in a multi-dimensional space, the minimum misclassification rate is obtained by using the Bayes criterion. Kernel estimators or probabilistic neural networks provide a good way to evaluate the probability densities of each class of data and are an interesting parallel implementation of the Bayesian classifier [1]. However, their training procedure leads to a very high number of neurons when large datasets are available;the classifier then becomes too complex and time consuming for on-line operation. Suboptimal Bayesian classifiers based on radial Gaussian kernels [2] uses an iterative unsupervised learning method based on vector quantization to obtain a significant simplification of the network structure, while keeping sufficiently accurate estimations of probability densities. In this paper, we study the vector quantization problem and the effects of codebook size and data space dimension on the optimal width factors of the radial Gaussian kernels used in the estimation. © 1995, Springer Verlag. All rights reserved.

关键词： Vector quantization

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27页 << < 18 19 20 21 22 23 24 25 26 27 > >>

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：