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
214 篇 期刊文献

馆藏范围

1,893 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

316 篇 工学
- 160 篇 计算机科学与技术...
- 157 篇 电气工程
- 63 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

1,893 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

1,790 篇 英文
96 篇 其他
7 篇 中文

检索条件"主题词=Backpropagation Algorithms"

共 1893 条记录，以下是261-270 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：

Stable dynamic backpropagation using constrained learning rate algorithm

Stable dynamic backpropagation using constrained learning ra...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Liang Jin M.M. Gupta P.N. Nikiforuk Intelligent Systems Research Laboratory College of Engineering University of Saskatchewan Saskatoon SAS Canada

An equilibrium point learning problem in discrete-time dynamic neural networks is studied in this paper using stable dynamic propagation with constrained learning rate algorithm. The new learning scheme provides an adaptive updating process of the synaptic weights of the network, so that the target pattern is stored at a stable equilibrium point. The applicability of the approach presented is illustrated through a binary pattern storage example.

关键词： backpropagation algorithms Nonlinear dynamical systems Neurons Recurrent neural networks Jacobian matrices Neural networks Stability Iterative algorithms Nonlinear equations Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

A new acceleration technique for the backpropagation algorithm

A new acceleration technique for the backpropagation algorit...

引用

International Conference on Neural Networks

作者： X. Yu N.K. Loh W.C. Miller Department of Electrical Engineering University of Windsor Windsor ONT Canada

An adaptive momentum algorithm which can update the momentum coefficient automatically in every iteration step is presented. The basic idea comes from the optimal gradient method. It is very difficult to obtain the optimal gradient vector by analytical methods, but it can be proven that the optimal gradient vectors in two successive iteration steps are orthogonal. Based on this property, one can use the Gram-Schmidt orthogonalization method to ensure the orthogonality of the successive gradient vectors. The result of this process is equivalent to adding a momentum term to the standard backpropagation algorithm. The momentum coefficient is updated automatically in every iteration. Numerical simulations show that the adaptive momentum algorithm can eliminate possible divergent oscillations during the initial training, and can also accelerate the learning process and result in a lower error when the final convergence is reached.< >

关键词： Acceleration backpropagation algorithms Gradient methods Multi-layer neural network Neural networks Feedforward neural networks Numerical simulation Read only memory Convergence of numerical methods Filters

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation for Training a Distributed backpropagation Implementation

Performance Evaluation for Training a Distributed BackPropag...

引用

International Symposium on Applied Computational Intelligence and Informatics ( SACI)

作者： Sorin Babii Department of Computer and Software Engineering Politehnica University of Timişoara Timisoara Romania

This paper presents the results of some experiments in parallelizing the training phase of a feed-forward, artificial neural network. More specifically, we develop and analyze a parallelization strategy of the widely used neural net learning algorithm called back-propagation. We describe an approach for parallelizing the back- propagation algorithm. We implemented these algorithms on several LANs, permitting us to evaluate and analyze their performances based on the results of actual runs. We were interested on the qualitative aspect of the analysis, in order to achieve a fair understanding of the factors determining the behavior of this parallel algorithms. We were interested in discovering and dealing with some of the specific circumstances that have to be considered when a parallelized neural net learning algorithm is to be implemented on a set of workstations in a LAN. Part of our purpose is to investigate whether it is possible to exploit the computational resources of such a set of workstations.

关键词： Algorithm design and analysis Artificial neural networks backpropagation algorithms Workstations Feedforward systems Performance analysis Performance evaluation Parallel algorithms Neural networks Local area networks

来源：评论

学校读者我要写书评

暂无评论

Reducing the number of multiplies in backpropagation

Reducing the number of multiplies in backpropagation

引用

International Joint Conference on Neural Networks (IJCNN)

作者： K. Boonyanit A.M. Peterson LSI Logic Corporation Milpitas CA USA STAR Lab Department of Electrical Engineering University of Stanford Stanford CA USA

There have been many algorithms to speed up the learning time of backpropagation. However, most of them do not take into consideration the amount of hardware required to implement the algorithm. Without suitable hardware implementation, the real promise of neural network applications will be difficult to achieve. Since multiply dominates computation and is expensive in hardware, this paper proposes a method to reduce the number of multiplies in the backward path of backpropagation algorithm by setting some neuron errors to zero. It proves the convergence theorem by the general Robbins-Monro process, a stochastic approximation process.< >

关键词： Neurons backpropagation algorithms Convergence Large scale integration Logic Neural network hardware Neural networks Stochastic processes Data flow computing Noise reduction

来源：评论

学校读者我要写书评

暂无评论

An automatic adjustment method of backpropagation learning parameters, using fuzzy inference

An automatic adjustment method of backpropagation learning p...

引用

International Symposium on Multiple-Valued Logic

作者： F. Ueno T. Inoue B.-u.-H. Baloch T. Yamamoto Department of Electrical Engineering and Computer Science Kumamoto University Kumamoto Japan Kure Works Babcock-Hitachi K.K. Hiroshima Japan

Fuzzy inference is introduced into a conventional backpropagation learning algorithm for neural networks. This procedure repeatedly adjusts the learning parameters and leads the system to convergence at the earliest possible time. The technique is appropriate in the sense that optimum learning parameters are being applied in every learning cycle automatically, whereas conventional backpropagation does not contain any well-defined rule regarding the proper selection of learning parameters.< >

关键词： backpropagation algorithms Neurons Multi-layer neural network Computer errors Neural networks Computer science Inference algorithms Temperature Computer simulation Mathematics

来源：评论

学校读者我要写书评

暂无评论

Content-based SMS spam filtering based on the Scaled Conjugate Gradient backpropagation algorithm

Content-based SMS spam filtering based on the Scaled Conjuga...

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Waddah Waheeb Rozaida Ghazali Mustafa Mat Deris Computer Science Department Hodeidah University Hodeidah Alduraihimi Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Batu Pahat Johor Universiti Tun Hussein Onn Malaysia Batu Pahat Johor MY

ISBN: (纸本)9781467376839

Content-based filtering is one of the most preferred methods to combat Short Message Service (SMS) spam. Memory usage and classification time are essential in SMS spam filtering, especially when working with limited resources. Therefore, suitable feature selection metric and proper filtering technique should be used. In this paper, we investigate how a learnt Artificial Neural Network with the Scaled Conjugate Gradient method (ANN-SCG) is suitable for content-based SMS spam filtering using a small size of features selected by Gini Index (GI) metric. The performance of ANN-SCG is evaluated in terms of true positive rate against false positive rate, Matthews Correlation Coefficient (MCC) and classification time. The evaluation results show the ability of ANN-SCG to filter SMS spam successfully with only one hundred features and a short classification time around to six microseconds. Thus, memory size and filtering time are reduced. An additional testing using unseen SMS messages is done to validate ANN-SCG with the one hundred features. The result again proves the efficiency of ANN-SCG with the one hundred features for SMS spam filtering with accuracy equal to 99.1%.

关键词： Measurement Feature extraction Training Indexes Artificial neural networks backpropagation algorithms Correlation

来源：评论

学校读者我要写书评

暂无评论

Genetic algorithm based pattern allocation schemes for training set parallelism in backpropagation neural networks

Genetic algorithm based pattern allocation schemes for train...

引用

IEEE International Conference on Evolutionary Computation

作者： Shou King Foo P. Saratchandran N. Sundararajan School of Electrical & Electronic Engineering Nanyang Technological University Singapore

Training set parallelization is an efficient method to optimize the training procedure performance of the backpropagation neural network algorithm. In training set parallelism, the training patterns are distributed 'optimally' among a heterogeneous array of processors, optimality criterion obtain the minimum training time per epoch. Earlier studies on heterogeneous transputers connected in a pipeline-ring topology have indicated that the above optimization problem results in a mixed integer programming problem and results in large computation time to find the optimal pattern allocations. In this paper, a genetic algorithm is used as an optimization tool to find the optimal allocation of patterns. The approach is illustrated using two benchmark problems, the 256-8-256 Encoder and NETTALK problems. Results indicate that when 'a priori' information is not used, the computation time needed by the genetic algorithm is comparable to that obtained by mixed integer programming. However, when 'a priori' information is used, the genetic algorithm results in significant reduction in computation time for finding the optimal solution.

关键词： Genetic algorithms Parallel processing backpropagation algorithms Linear programming Neural networks Intelligent networks Optimization methods Network topology Multi-layer neural network Analytical models

来源：评论

学校读者我要写书评

暂无评论

Discovery of backpropagation learning rules using genetic programming

Discovery of backpropagation learning rules using genetic pr...

引用

IEEE International Conference on Evolutionary Computation

作者： A. Radi R. Poli School of Computer Science University of Binningham Birmingham UK

The backpropagation learning rule is widespread computational method for training multilayer networks. Unfortunately, backpropagation suffers from several problems. The authors have used genetic programming (GP) to overcome some of these problems and to discover new supervised learning algorithms. A set of such learning algorithms has been compared with the standard backpropagation (SBP) learning algorithm on different problems and has been shown to provide better performances. The study indicates that there exist many supervised learning algorithms better than, but similar to, SEP and that GP can be used to discover them.

关键词： Genetic programming backpropagation algorithms Supervised learning Computer networks Humans Computer science Electronic mail Nonhomogeneous media Artificial neural networks Multi-layer neural network

来源：评论

学校读者我要写书评

暂无评论

A backpropagation algorithm which automatically determines the number of association units

A backpropagation algorithm which automatically determines t...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： K. Murase Y. Matsunaga Y. Nakade Department of Information Science Fukui University of Technology Fukui Japan

Presents a modified backpropagation algorithm which iteratively cuts out or adds association units during the learning process, and which is expected to form networks with the minimal number of association units for given learning problems. The principle is rather simple: when the calculation by the conventional backpropagation converges, the effectiveness of each association unit is assessed by the goodness factor and the unit having the least value of it in the layer is removed. On the other hand, when it does not converge, a new unit is added. The goodness factor is defined to represent the total amount of feedforward-propagated signal by the unit, and is easily calculated. In all the learning problems tested, the minimal or nearly minimal networks for the given problems were obtained with high probability. Some examples are presented.< >

关键词： backpropagation algorithms Iterative algorithms Information science Testing Neural networks Character recognition Flowcharts

来源：评论

学校读者我要写书评

暂无评论

Nonmonotone methods for backpropagation training with adaptive learning rate

Nonmonotone methods for backpropagation training with adapti...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： V.P. Palgianakos M.N. Vrahatis G.D. Magoulas Dept. of Math. Patras Univ. Greece Department of Mathematics U.P. Artificial Intelligence Research Center-UPAIRC University of Patras Patras Greece Department of Informatics U.P. Artificial Intelligence Research Center-UPAIRC University of Athens (NKUA) Athens Greece

We present nonmonotone methods for feedforward neural network training, i.e., training methods in which error function values are allowed to increase at some iterations. More specifically, at each epoch we impose that the current error function value must satisfy an Armijo-type criterion, with respect to the maximum error function value of M previous epochs. A strategy to dynamically adapt M is suggested and two training algorithms with adaptive learning rates that successfully employ the above mentioned acceptability criterion are proposed. Experimental results show that the nonmonotone learning strategy improves the convergence speed and the success rate of the methods considered.

关键词： Convergence Artificial intelligence Neural networks Learning Mathematics Feedforward neural networks backpropagation algorithms Informatics Artificial neural networks Tires

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 << < 23 24 25 26 27 28 29 30 31 32 > >>

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：