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

31 篇 会议
1 篇 期刊文献

馆藏范围

32 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

6 篇 工学
- 6 篇 计算机科学与技术...
- 5 篇 软件工程
- 1 篇 信息与通信工程
- 1 篇 控制科学与工程
5 篇 理学
- 3 篇 系统科学
- 2 篇 数学
- 2 篇 物理学

主题

16 篇 artificial neura...
12 篇 neural networks
9 篇 neurons
9 篇 laboratories
8 篇 circuits
6 篇 neurofeedback
6 篇 very large scale...
6 篇 computer network...
5 篇 hopfield neural ...
5 篇 equations
5 篇 circuits and sys...
4 篇 analog computers
3 篇 circuit simulati...
3 篇 state feedback
3 篇 computer archite...
3 篇 prototypes
3 篇 signal processin...
3 篇 neural network h...
3 篇 vectors
3 篇 image processing

机构

9 篇 systems and circ...
5 篇 circuits and sys...
3 篇 system and circu...
3 篇 system and circu...
2 篇 circuits and sys...
2 篇 circuits systems...
2 篇 ic tech inc. oke...
1 篇 department of co...
1 篇 circuits and sys...
1 篇 system and circu...
1 篇 systems and circ...
1 篇 systems and circ...
1 篇 systems and circ...
1 篇 circuits and sys...
1 篇 dept. of electr....
1 篇 ic technology in...
1 篇 systems and circ...
1 篇 circuits and sys...
1 篇 department of co...

作者

20 篇 f.m.a. salam
5 篇 g. erten
5 篇 b. ling
4 篇 s.s. vedula
4 篇 salam fathi m.a.
4 篇 y. wang
2 篇 m.-r. choi
2 篇 f.m. salam
2 篇 j. hou
2 篇 hou jiansheng
2 篇 fathi m.a. salam
2 篇 ahmad maqbool
2 篇 salam fathi m. a...
2 篇 ling bo
1 篇 myung-ryul choi
1 篇 hwa-joon oh
1 篇 salam f.m.a.
1 篇 s. vedula
1 篇 wang yiwen
1 篇 m. ahmad

语言

32 篇 英文

检索条件"机构=Systems and Circuits and Artificial Neural Nets Laboratories"

共 32 条记录，以下是11-20 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：

An analytical learning algorithm for the dendro-dendritic artificial neural network via linear programming

An analytical learning algorithm for the dendro-dendritic ar...

引用

International Conference on neural Networks

作者： B. Ling F.M.A. Salam Circuits and Systems & Artijicial Neural Nets Laboratories Departmenr of Electrical Engineering Michigan State University East Lansing MI USA

An analytical learning algorithm to find the weight matrix of the dendro-dendritic neural network is presented. This learning algorithm utilizes linear programming to find all (necessarily) non-negative and small weights. A sufficient stability criterion is given, which guarantees all stored patterns to be asymptotically stable.< >

关键词： Algorithm design and analysis artificial neural networks neural networks Linear programming Neurons Stability criteria Neurofeedback Hopfield neural networks Very large scale integration MOSFETs

来源：评论

学校读者我要写书评

暂无评论

Data-driven subthreshold analog circuit that computes principal components

Data-driven subthreshold analog circuit that computes princi...

引用

Midwest Symposium on circuits and systems (MWSCAS)

作者： F.M.A. Salam S.S. Vedula Circuits and Systems and Artificial Neural Networks Laboratories Department of Electrical Engineering Michigan State University East Lansing MI USA

We present a model for the computation of principal components that is tailored for circuit realization. The model uses MOS elements and differential pairs which operate in the subthreshold regime of MOS operation. Co... 详细信息

关键词： Analog circuits Analog computers Equations Vectors Symmetric matrices Eigenvalues and eigenfunctions Power system modeling Computer networks Remuneration circuits and systems

来源：评论

学校读者我要写书评

暂无评论

Subthreshold analog feature matching circuits with large output voltages

Subthreshold analog feature matching circuits with large out...

引用

Midwest Symposium on circuits and systems (MWSCAS)

作者： B. Ling S.S. Vedula F.M.A. Salam Circuits and Systems and Artificial Neural Networks Laboratories Department of Electrical Engineering Michigan State University East Lansing MI USA

We present (subthreshold) analog bump circuits with a view towards obtaining large output voltage swings. These large swings can be useful in transferring voltage information to the outside world or to a (digital) computer. We also use some of these circuits to compare the similarity of patches in two images as part of the solution to stereo vision. In this case, considering two n/spl times/n patches, the circuit consists of n/sup 2/ building blocks. Each block operates in the subthreshold region with analog input voltages and analog output currents/voltages.< >

关键词： Stereo vision Circuit simulation Pixel Mirrors Shape Threshold voltage circuits and systems artificial neural networks laboratories Windows

来源：评论

学校读者我要写书评

暂无评论

A PRODUCT-OF-NORMS MODEL FOR RECURRENT neural NETWORKS

A PRODUCT-OF-NORMS MODEL FOR RECURRENT NEURAL NETWORKS

引用

1992 International Joint Conference on neural Networks, IJCNN 1992

作者： Hou, Jiansheng Salam, Fathi M.A. Systems and Circuits & Artificial Neural Nets Laboratories Department of Electrical Engineering Michigan State University East LansingMI48824 United States

ISBN: (纸本)0780305590

We present a model for recurrent artificial neural networks which can store any number of any pre-specified patterns as energy local minima. Therefore, all the pre-specified patterns can be stored and retrieved. We summarize the model's stability properties. We then give two demonstrative examples showing how this model can be used in image recognition and association. © 1992 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Dynamic Learning Using Exponential Energy Functions

Dynamic Learning Using Exponential Energy Functions

引用

1992 International Joint Conference on neural Networks, IJCNN 1992

作者： Ahmad, Maqbool Salam, Fathi M.A. System and Circuits and Artificial Neural Nets Laboratories Department of Electrical Engineering Michigan State University East LansingMI48824 United States

ISBN: (纸本)0780305590

We employ a continuous-time gradient descent weight update law for supervised learning of feedforward artificial neural networks due to specific advantages over its discrete-time counterpart. We also employ an Exponential energy function in the update law. We analytically show that this energy function would speed up the learning dynamics and ensures faster convergence to a useful minimum. The dynamics would "skip" minima which are at higher energy levels and converge to one at a lower energy level. We also describe software implementation of the learning dynamics based on the Exponential energy function. Various supporting simulations on the XOR and character recognition problems are also included. © 1992 IEEE

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

A cellular network formed of Hopfield networks 35

A cellular network formed of Hopfield networks

引用

35th Midwest Symposium on circuits and systems, MWSCAS 1992

作者： Ling, Bo Salam, Fathi M. A. System and Circuits and Artificial Neural Nets Laboratories Department of Electrical Engineering Michigan State University East LansingMI48824 United States

ISBN: (纸本)0780305108

In this paper, we introduce a general structure of cellular Hopfield neural network. An analytical method is presented to find weight matrix for a given set of desired vectors. An energy function is then constructed. Using the energy function, we give a sufficient stability criterion which can be realized by a redesign of the neuron function. © 1992 IEEE.

关键词： Hopfield neural networks

来源：评论

学校读者我要写书评

暂无评论

Error back-propagation learning using polynomial energy function

引用

1992 IEEE International Conference on systems Engineering

作者： Ahmad, Maqbool Salam, Fathi M. A. System and Circuits and Artificial Neural Nets Laboratories Department of Electrical Engineering Michigan State University East LansingMI48824 United States

ISBN: (纸本)0780307348

The sum-of-the-squared energy function used in the gradient descent weight update law for supervised (error back-propagation) learning of feedforward artificial neural networks, is basically the L2 (Euclidian) norm. A Polynomial energy function of order r, is a combination of all the Lp norms ( 1 1 and the L2 norms. We also describe software implementation of the learning dynamics based on the Polynomial energy function. Various supporting simulations on the typical XOR problem are also included. © 1992 IEEE.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

A recurrent dynamic network for associative recall

引用

1992 IEEE International Conference on systems Engineering

作者： Hou, Jiansheng Salam, Fathi M.A. System and Circuits and Artificial Neural Nets Laboratories Department of Electrical Engineering Michigan State University East LansingMI48824 United States

ISBN: (纸本)0780307348

We have presented a model for recurrent artificial neural networks which can store any number of any pre-specified patterns as energy local minima. Therefore, all the pre-specified patterns can be stored and recalled. Some demonstrative examples are given to show how this model can be used in image recognition and association. Generalization of the energy function is discussed. Variations of this model are also investigated for performance improvement and potential hardware implementation. © 1992 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

A product-of-norms model for recurrent neural networks

A product-of-norms model for recurrent neural networks

引用

International Joint Conference on neural Networks (IJCNN)

作者： J. Hou F.M.A. Salam Systems and Circuits & Artificial Neural Nets Laboratories Department of Electrical Engineering Michigan State University East Lansing MI USA

The authors present a model for recurrent artificial neural networks which can store any number of any prespecified patterns as energy local minima. Therefore, all the prespecified patterns can be stored and retrieved. The authors summarize the model's stability properties. They then give two examples, showing how this model can be used in image recognition and association.< >

关键词： Recurrent neural networks Neurons artificial neural networks Stability circuits laboratories Image recognition Computer networks Control systems Adaptive control

来源：评论

学校读者我要写书评

暂无评论

A recurrent dynamic network for associative recall

A recurrent dynamic network for associative recall

引用

IEEE International Conference on systems Engineering

作者： J. Hou F.M.A. Salam System and Circuits & Artificial Neural Nets Laboratories Department of Electrical Engineering Michigan State University East Lansing MI USA

A model for recurrent artificial neural networks which can store any number of any prespecified patterns as energy local minima is presented. Therefore, all the prespecified patterns can be stored and recalled. Some examples are given to show how this model can be used in image recognition and association. Generalization of the energy function is discussed. Variations of this model are also investigated for performance improvement and potential hardware implementation.< >

关键词： Neurons artificial neural networks Computer networks Mathematical model Equations circuits laboratories Electronic mail neural network hardware neural networks

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4页 << < 1 2 3 4 > >>

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：