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

1,679 篇 会议
213 篇 期刊文献

馆藏范围

1,892 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

315 篇 工学
- 159 篇 计算机科学与技术...
- 157 篇 电气工程
- 62 篇 控制科学与工程
- 46 篇 电子科学与技术（可...
- 30 篇 软件工程
- 21 篇 信息与通信工程
- 14 篇 机械工程
- 13 篇 仪器科学与技术
- 6 篇 测绘科学与技术
- 6 篇 生物医学工程（可授...
- 4 篇 材料科学与工程（可...
- 4 篇 动力工程及工程热...
- 3 篇 核科学与技术
- 3 篇 网络空间安全
- 2 篇 力学（可授工学、理...
- 2 篇 石油与天然气工程
- 2 篇 船舶与海洋工程
- 2 篇 航空宇航科学与技...
- 2 篇 生物工程
49 篇 理学
- 15 篇 物理学
- 12 篇 系统科学
- 9 篇 数学
- 6 篇 地球物理学
- 3 篇 生物学
- 2 篇 化学
39 篇 管理学
- 37 篇 管理科学与工程(可...
14 篇 医学
- 10 篇 临床医学
- 4 篇 基础医学(可授医学...
- 2 篇 特种医学
4 篇 农学
- 3 篇 作物学
2 篇 军事学
1 篇 文学
1 篇 艺术学

主题

1,892 篇 backpropagation ...
1,270 篇 neural networks
463 篇 artificial neura...
453 篇 neurons
327 篇 multi-layer neur...
297 篇 convergence
289 篇 feedforward neur...
211 篇 multilayer perce...
197 篇 computer network...
191 篇 testing
126 篇 algorithm design...
125 篇 pattern recognit...
122 篇 computer science
119 篇 intelligent netw...
112 篇 recurrent neural...
110 篇 equations
107 篇 fuzzy neural net...
106 篇 training data
100 篇 control systems
100 篇 signal processin...

机构

12 篇 school of electr...
11 篇 department of el...
9 篇 department of el...
7 篇 department of el...
5 篇 at and t bell la...
5 篇 computer science...
5 篇 faculty of engin...
4 篇 school of inform...
4 篇 department of el...
4 篇 department of el...
4 篇 center for infor...
4 篇 departamento de ...
4 篇 center for robot...
4 篇 department of co...
4 篇 departamento de ...
4 篇 department of el...
4 篇 esstt tunis tuni...
3 篇 international co...
3 篇 department of co...
3 篇 department of el...

作者

13 篇 wen yu
9 篇 n.j. bershad
8 篇 k. nakayama
8 篇 k.y. lee
7 篇 h.k. kwan
7 篇 j.c. principe
7 篇 j.j. shynk
6 篇 w.c. miller
6 篇 n.k. loh
6 篇 m.t. hagan
6 篇 p. saratchandran
6 篇 chin-teng lin
6 篇 xiaoou li
6 篇 k. hirasawa
6 篇 n. sundararajan
5 篇 g.v. puskorius
5 篇 l.a. feldkamp
5 篇 f. fnaiech
5 篇 f. piazza
5 篇 d.w. tufts

语言

1,789 篇 英文
96 篇 其他
7 篇 中文

检索条件"主题词=Backpropagation Algorithms"

共 1892 条记录，以下是1751-1760 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：

Double backpropagation increasing generalization performance

Double backpropagation increasing generalization performance

引用

International Joint Conference on Neural Networks (IJCNN)

作者： H. Drucker Y. Le Cun AT and T Bell Laboratories Inc. West Long Branch NJ USA AT and T Bell Laboratories Inc. Holmdel NJ USA

One test of a training algorithm is how well the algorithm generalizes from the training data to the test data. It is shown that a training algorithm termed double back-propagation improves generalization by simultaneously minimizing the normal energy term found in back-propagation and an additional energy term that is related to the sum of the squares of the input derivatives (gradients). In normal back-propagation training, minimizing the energy function tends to push the input gradient to zero. However, this is not always possible. Double back-propagation explicitly pushes the input gradients to zero, making the minimum broader, and increases the generalization on the test data. The authors show the improvement over normal back-propagation on four candidate architectures with a training set of 320 handwritten numbers and a test set of size 180.< >

关键词： Neurons backpropagation algorithms Testing Educational institutions Training data Ear Transfer functions Equations

来源：评论

学校读者我要写书评

暂无评论

Statistical analysis of the single-layer backpropagation algorithm

Statistical analysis of the single-layer backpropagation alg...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： N.J. Bershad J.J. Shynk P.L. Feintuch Department of Electrical and Computer Engineering University of California Irvine CA USA Center of Information Processing Research Department of Electrical and Computer Engineering University of California Santa Barbara CA USA Hughes Aircraft Company Fullerton CA USA

The authors present a statistical analysis of the steady-state and transient properties of the single-layer backpropagation algorithm for Gaussian input signals. It is based on a nonlinear system identification model of the desired response which is capable of generating an arbitrary hyperplane decision boundary. It is demonstrated that, although the weights grow unbounded, the mean-square error decreases towards zero. These results indicate that the algorithm, on average, quickly learns the correct hyperplane associated with the system identification model. However, the nature of the mean-square error and the corresponding performance surface are such that the perceptron is prevented from correctly classifying with probability one until the weights converge at infinity.< >

关键词： Statistical analysis backpropagation algorithms System identification Vectors Steady-state Signal processing Signal generators Information processing Aircraft propulsion Transient analysis

来源：评论

学校读者我要写书评

暂无评论

A combined method for improving backpropagation algorithm

A combined method for improving backpropagation algorithm

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： D.-C. Lee B.-J. Kim J.-M. Yun E.-Y. Cha Department of Computer Science Pusan National University busan South Korea

The authors present a new approach, called a combined method, for improving the backpropagation algorithm. They describe the standard backpropagation learning method and Newton's method. Experiments on three problems are reported: exclusive-OR, the encoder and the parity problem. The learning speeds are compared by epochs and CPU time. The performance of the combined method and Newton's method is compared. Experiments show that the combined method is faster than the standard backpropagation in epochs and more efficient than Newton's method in spaces and computations.< >

关键词： backpropagation algorithms Newton method Neural networks Learning systems Information processing Cost function Computer science Neurons Associative memory Filtering

来源：评论

学校读者我要写书评

暂无评论

Recurrent and feedforward backpropagation for time independent pattern recognition

Recurrent and feedforward backpropagation for time independe...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： H. Behrens D. Gawronska J. Hollatz B. Schurmann Institut für Informatik TU München Munchen Germany Universität der Bundeswehr Munich Munchen Germany Corporate Research and Development Siemens AG Munchen Germany

Based on a unified description of neural algorithms for time-independent pattern recognition, the authors discuss the generalization ability of a three-layer perceptron for recurrent backpropagation depending on the number of learning epochs and the steepness of the neurons' threshold function. Moreover, the suitability of recurrent and feedforward backpropagation learning algorithms for implementation on multiprocessor systems is investigated. In contrast to the common belief that recurrent back-propagation is more computationally intensive than feedforward backpropagation, the present results for optical character recognition indicate that this need not be the case if the steepness of the threshold function is appropriately chosen. This makes recurrent backpropagation a suitable candidate for time-independent pattern recognition.< >

关键词： Pattern recognition backpropagation algorithms Neurons Multiprocessing systems Equations Neurofeedback Neural networks Computer architecture Concurrent computing Image processing

来源：评论

学校读者我要写书评

暂无评论

On a generalised backpropagation algorithm based on optimal control theory

On a generalised backpropagation algorithm based on optimal ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： W.S. Cheung J.K. Hammond Signal Processing and Control Group Institute of Sound and Vibration Research University of Southampton Southampton UK

A novel learning mechanism for the multilayered neural network is formulated as the optimal trajectory along which the state and weight vector of each layer should evolve. This approach leads to a rigorous proof of the backpropagation algorithm, points out several limitations of the generalized delta rule, and presents a way of overcoming them. A simple network is examined as the model for solving a nonlinear system identification problem. Simulated results reveal that the asymptotic accuracy and the convergence rate of the proposed algorithm are superior to those of the standard algorithm.< >

关键词： backpropagation algorithms Optimal control Neural networks Neurons Multi-layer neural network Feedforward neural networks Signal processing algorithms Control theory Nonlinear systems Yttrium

来源：评论

学校读者我要写书评

暂无评论

Higher degree error backpropagation in cross-coupled Hopfield nets

Higher degree error backpropagation in cross-coupled Hopfiel...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： K. Tsutsumi Faculty of Science and Technology Ryukoku University Otsu Japan

The author discusses higher-degree error backpropagation in cross-coupled Hopfield nets employing exponential energy functions for cross-coupling. He constructs a Lyapunov function to derive a total network architecture and a learning algorithm for training nonlinear multilayered internetworks. In the derived architecture, each internetwork for cross-coupling has a forward subnet and a backward subnet. The backward subnet consists of multiple planes, each of which has the same connection weights as those in the forward subnet. From linear to higher degree errors respectively backpropagate in the different planes. The final outputs from the multiple planes are utilized effectively for network relaxation. At the same time, the interactions between the errors in each plane and the signals in the forward subnet contribute to the connectionistic learning. The result obtained indicates that higher-degree error backpropagation is effective for fast learning.< >

关键词： Lyapunov method Internet IP networks Intelligent networks Paper technology backpropagation algorithms Artificial neural networks Feedback loop State feedback Magnesium compounds

来源：评论

学校读者我要写书评

暂无评论

An implementation of backpropagation algorithm on a massively parallel processor

An implementation of backpropagation algorithm on a massivel...

引用

Southeastern Symposium on System Theory

作者： O.M. Omidvar C.L. Wilson University of District of Columbia Washington D.C. DC USA National Institute for Standards and Technology Gaithersburg MD USA

The backpropagation learning algorithm has been modified to operate in a massively parallel environment. The network has 1024 neurons in the first layer; there are two hidden layers, either of which can be activated on demand. The first hidden layer has 256 neurons and the second hidden layer has only 64 neurons. The output layer has only ten different classes. The network operates in concurrent and parallel manner. All incoming signals are fed to the input layer at the same time, and they are processed and passed to subsequent stages in tandem. The connections are created at random with normal distributions. The error is calculated not one at the time, but simultaneously for all the classes, then resulted errors are used for calculation of total error in the network. The network is applied to the task of character recognition, using Gabor image coefficients.< >

关键词： backpropagation algorithms Character recognition Neural networks Image recognition Neurons Image segmentation NIST Signal processing Gaussian distribution Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Heuristic configuration of hidden units, in backpropagation neural networks

Heuristic configuration of hidden units, in backpropagation ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： N. Indurkhya S.M. Weiss Department of Computer Science Rutgers University New Brunswick NJ USA

Summary form only given, as follows. For optimum statistical classification and generalization with single hidden-layer backpropagation neural network models, two tasks must be performed: (a) learning the best set of weights for a network of k hidden units and (b) determining k, the best complexity fit. Two approaches to learning have been contrasted: (a) standard backpropagation as applied to a series of networks with different numbers of hidden units; and (b) a heuristic cascade-correlation approach that quickly and dynamically learns and configures a network. Four real-world statistical applications were considered. On these examples, the backpropagation approach yielded somewhat better results, but with far greater computation times. The best k's for the two approaches were quite similar, suggesting a hybrid approach that chooses k by cascade-correlation, and optimizes the weights by backpropagation.< >

关键词： Intelligent networks Neural networks Convergence backpropagation algorithms Computer science Algorithm design and analysis Matrices Cost function Adaptive control

来源：评论

学校读者我要写书评

暂无评论

Effect of parameter value and initial weights on the performance of backpropagation algorithm

Effect of parameter value and initial weights on the perform...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： M. Wann US Naval Air Dev. Center Warminster PA USA

Summary form only given, as follows. A feedforward neural network learning XOR task was used to demonstrate the influence of initial weights on the convergence behavior of the algorithm. Using selected initial weight sets, a series of deterministic experiments was then performed to determine the effect of learning rate and momentum on the convergence of the algorithm and time of convergence. The results show that there is a trade-off in choosing parameter values for faster convergence and that multiple global minima exist in the error surface.< >

关键词： backpropagation algorithms Encoding Convergence Feedforward systems Neural networks Feedforward neural networks Associative memory Magnesium compounds Equations Sonar

来源：评论

学校读者我要写书评

暂无评论

Feature detectors and difference operators in BP networks

Feature detectors and difference operators in BP networks

引用

International Joint Conference on Neural Networks (IJCNN)

作者： D.F. Michaels Dept. of Electr. Eng. & Comput. Sci. Colorado Univ. Denver CO USA

Summary form only given, as follows. Hidden units are commonly thought to function as feature detectors. In the present work it was shown, however, that hidden units in networks trained using the backpropagation (BP) algorithm actually function as difference, or novelty, detectors most of the time. This was illustrated in four ways: (1) the form of the hidden unit weight vectors, (2) correlations between these weights and the training patterns, (3) the vectors obtained when these weights are multiplied by various input patterns, and (4) the weight vectors obtained from a piecewise linearized model of the network.< >

关键词： Computer vision Intelligent networks Computer science Gas detectors backpropagation algorithms

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190页 << < 172 173 174 175 176 177 178 179 180 181 > >>

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：