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

70 篇 会议
33 篇 期刊文献

馆藏范围

103 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

40 篇 工学
- 19 篇 计算机科学与技术...
- 17 篇 软件工程
- 11 篇 电子科学与技术（可...
- 10 篇 电气工程
- 8 篇 生物工程
- 7 篇 信息与通信工程
- 6 篇 动力工程及工程热...
- 5 篇 生物医学工程（可授...
- 3 篇 控制科学与工程
- 2 篇 光学工程
- 2 篇 材料科学与工程（可...
- 1 篇 仪器科学与技术
- 1 篇 土木工程
- 1 篇 化学工程与技术
- 1 篇 船舶与海洋工程
- 1 篇 航空宇航科学与技...
- 1 篇 农业工程
25 篇 理学
- 12 篇 生物学
- 11 篇 数学
- 5 篇 物理学
- 3 篇 统计学（可授理学、...
- 2 篇 化学
- 2 篇 系统科学
- 1 篇 海洋科学
10 篇 医学
- 9 篇 临床医学
- 7 篇 基础医学(可授医学...
- 2 篇 药学(可授医学、理...
4 篇 农学
- 2 篇 作物学
1 篇 法学
- 1 篇 社会学
1 篇 管理学
- 1 篇 管理科学与工程(可...

主题

24 篇 laboratories
17 篇 neural networks
12 篇 computer science
8 篇 neurons
7 篇 training data
5 篇 cellular neural ...
5 篇 very large scale...
5 篇 humans
5 篇 testing
5 篇 computer network...
4 篇 turing machines
4 篇 application soft...
4 篇 signal to noise ...
4 篇 computational mo...
4 篇 image processing
4 篇 circuits
4 篇 artificial neura...
4 篇 robustness
3 篇 cmos integrated ...
3 篇 automation

机构

9 篇 artificial neura...
4 篇 department of co...
4 篇 artificial neura...
3 篇 department of co...
3 篇 circuits systems...
3 篇 department of el...
3 篇 laboratory for a...
3 篇 artificial neura...
2 篇 department of ps...
2 篇 school of mathem...
2 篇 department of ne...
2 篇 riken aip japan.
2 篇 max planck insti...
2 篇 massachusetts ge...
2 篇 department of bi...
2 篇 nuctech netherla...
2 篇 tencent ai lab c...
2 篇 allen institute ...
2 篇 texas a&m univer...
2 篇 institute for br...

作者

15 篇 r. kothari
5 篇 t. roska
4 篇 l.o. chua
3 篇 k. agyepong
3 篇 t. balachander
3 篇 fathi salem
3 篇 zaid albataineh
3 篇 jung tzyy-ping
3 篇 j. ghosh
3 篇 chua leon o.
3 篇 kothari ravi
3 篇 faisal t. abu-ni...
3 篇 fathi m. salem
2 篇 li cheng
2 篇 ching-wei wang
2 篇 georgia tourassi
2 篇 todd gillette
2 篇 roska tamás
2 篇 miroslav radojev...
2 篇 s. grossberg

语言

99 篇 英文
3 篇 其他
1 篇 中文

检索条件"机构=Department of Congnitive and Neural Systems and Electrical and Computer Engineering"

共 103 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：

Familiarity discrimination of radar pulses 98

Familiarity discrimination of radar pulses

引用

Proceedings of the 12th International Conference on neural Information Processing systems

作者： Eric Granger Stephen Grossberg Mark A. Rubin William W. Streilein Department of Electrical and Computer Engineering École Poly technique de Montréal Montreal Qc. Canada Department of Cognitive and Neural Systems Boston University Boston MA

The ARTMAP-FD neural network performs both identification (placing test patterns in classes encountered during training) and familiarity discrimination (judging whether a test pattern belongs to any of the classes encountered during training). The performance of ARTMAP-FD is tested on radar pulse data obtained in the field, and compared to that of the nearest-neighbor-based NEN algorithm and to a k > 1 extension of NEN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High speed calculation of cryptographic hash functions by CNN chips

High speed calculation of cryptographic hash functions by CN...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： M. Csapodi J. Vandewalle T. Roska Analogic and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary ESAT Laboratory Department of Electrical Engineering Katholieke Universiteit Leuven Leuven Belgium

The paper is concerned with the implementation of cryptographic hash functions on the regular array of simple cellular neural network (CNN) cells with periodic boundary conditions. Cryptographic hash functions enable message origin authentication and validation of message content integrity. A class of cryptographic hash functions-termed Cartesian authentication codes-provide provable (unconditional) security for message authentication between two mutually trustful parties sharing a secret key. We succeeded in implementing existing constructions of Cartesian authentication codes on today's CNN Universal Machine (CNN-UM) chips. Here we prove that rather complex (binary) arithmetic can be performed on a simple CNN chip, by providing an algorithm to implement a specific Cartesian authentication code based on the computation of a polynomial expression over a finite field. The bitrate of the computation is in the 100 Mbit/sec range with existing chips.

关键词： Cryptography Cellular neural networks Message authentication Laboratories Galois fields Automation Boundary conditions Turing machines Arithmetic Bit rate

来源：评论

学校读者我要写书评

暂无评论

Floating-gate CMOS analog memory cell array

Floating-gate CMOS analog memory cell array

引用

IEEE International Symposium on Circuits and systems (ISCAS)

作者： R.R. Harrison P. Hasler B.A. Minch Computation and Neural Systems Program 139-74 California Institute of Technology NASA Pasadena CA USA Department of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA School of Electrical Engineering Cornell University Ithaca NY USA

The complexity of analog VLSI systems is often limited by the number of pins on a chip rather than by the die area. Currently, many analog parameters and biases are stored off chip. Moving parameter storage on chip could save pins and allow us to create complex programmable analog systems. In this paper, we present a design for an on-chip non-volatile analog memory cell that can be configured in addressable arrays and programmed easily. We use floating-gate MOS transistors to store charge, and we use the processes of tunneling and hot-electron injection to program values. We achieve greater than 13-bit precision with no crosstalk between memory cells.

关键词： Nonvolatile memory Analog memory Pins Voltage Potentiometers Tunneling Very large scale integration Secondary generated hot electron injection Analog computers CMOS technology

来源：评论

学校读者我要写书评

暂无评论

Self-regulation of model order in feed-forward neural networks

Self-regulation of model order in feed-forward neural networ...

引用

1997 IEEE International Conference on neural Networks (ICNN 97)

作者： Kothari, R Agyepong, K Artificial Neural Systems Laboratory Department of Electrical and Computer Engineering and Computer Science University of Cincinnati Cincinnati OH 45221-0030 United States

ISBN: (纸本)0780341236

Despite the presence of theoretical results, the application of feed-forward neural networks is hampered by the lack of systematic procedural methods for determining the number of hidden neurons to use. The number of hidden layer neurons determine the order of the neural network model and consequently the generalization performance of the network. This paper puts into perspective the approaches used to address this problem and presents a new paradigm which uses dependent evolution of hidden layer neurons to self-regulate the model order. We show through simulations that despite an abundance of free-parameters (i.e. starting with a larger than necessary network, the proposed paradigm allows for localization of specializing hidden layer neurons with the unspecialized hidden layer neurons behaving similarly. These similarly behaving neurons reduce the model order and allow for the benefits of a smaller sized network. Hints on analytically understanding the behavior are also noted.

关键词： Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Effect of pruning small weights in correlation associative memories

Effect of pruning small weights in correlation associative m...

引用

1997 IEEE International Conference on neural Networks, ICNN 1997

作者： Kothari, R. Lotlikar, R. Artificial Neural Systems Laboratory Department of Electrical and Computer Engineering and Computer Science University of Cincinnati Cincinnati OH 45221-0030 United States

ISBN: (纸本)0780341228

In this paper we examine the effect of pruning small weights in correlation associative memories. The effect is investigated by considering a fully interconnected matrix and removing weights satisfying |w|Ε. We show analytically that under suitable constraints on Ε, the capacity of a sparsely connected associative memory is comparable to that of a fully connected one, without compromising the basins of attraction around the prototype fixed points. Simulation results supporting the analysis are also presented. © 1997 IEEE.

关键词： Associative processing

来源：评论

学校读者我要写书评

暂无评论

An empirical comparison of dimensionality reduction techniques for pattern classification 7th

An empirical comparison of dimensionality reduction techniqu...

引用

7th International Conference on Artificial neural Networks, ICANN 1997

作者： Balachander, Thiagarajan Kothari, Ravi Cualing, Hernani Artificial Neural Systems Laboratory Department of Electrical and Computer Engineering and Computer Science United States Department of Pathology and Lab. Medicine University of Cincinnati CincinnatiOH45221 United States

ISBN: (纸本)3540636315

To some extent or other all classifiers are subject to the curse of dimensionality. Consequently, pattern classification is often preceded with finding a reduced dimensional representation of the patterns. In this paper we empirically compare the performance of unsupervised and supervised dimensionality reduction techniques. The data set we consider is obtained by segmenting cells in cytological preparations and extracting 9 features from each of the cells. We evaluate the performance of 4 dimensionality reduction techniques (2 unsupervised) and (2 supervised) with and without noise. The unsupervised techniques include principal component analysis and self-organizing feature maps, while the supervised techniques include Fisher's linear discriminants and multi-layered feed-forward neural networks. Our results on a real world data set indicate that multi-layered feed-forward neural networks outperform the other three dimensionality reduction techniques and that all techniques are sensitive to noise. © Springer-Verlag Berlin Heidelberg 1997.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

Effect of pruning small weights in correlation associative memories

Effect of pruning small weights in correlation associative m...

引用

International Conference on neural Networks

作者： R. Kothari R. Lotlikar Artificial Neural Systems Laboratory Department of Electrical & Computer Engineering & Computer Science University of Cincinnati Cincinnati OH USA

In this paper we examine the effect of pruning small weights in correlation associative memories. The effect is investigated by considering a fully interconnected matrix and removing weights satisfying |w/sub ij/|/spl les//spl epsiv/. We show analytically that under suitable constraints on /spl epsiv/, the capacity of a sparsely connected associative memory is comparable to that of a fully connected one, without compromising the basins of attraction around the prototype fixed points. Simulation results supporting the analysis are also presented.

关键词： Associative memory Neurons neural networks Image storage Prototypes Laboratories computer science Analytical models Image retrieval Image restoration

来源：评论

学校读者我要写书评

暂无评论

Optical flow determination using topology preserving mappings

Optical flow determination using topology preserving mapping...

引用

IEEE International Conference on Image Processing

作者： R. Kothari J. Bellando Artificial Neural Systems Laboratory Department of Electrical & Computer Engineering & Computer Science University of Cincinnati Cincinnati OH USA

Determining the optical flow is an ill-posed problem, and requires the inclusion of a regularization term for solution. We show that ordered maps produced through self-organization reflect the topological relationships of the input, and can thus inherently supply the constraints required in obtaining the optical flow. Our computational procedure is thus based on training a self-organizing feature map with features from the first frame of an image sequence, and observing the displacement weights in the weights when, the network is subsequently trained with features drawn from the second frame. We show through four simulations (three single object, and one multiple object) that the weight displacements provide an accurate representation of the optical flow.

关键词： Image motion analysis Topology Neurons Laboratories Optical computing computer science Image sequences Computational modeling Constraint theory Lighting

来源：评论

学校读者我要写书评

暂无评论

Induced specialization of context units for temporal pattern recognition and reproduction

Induced specialization of context units for temporal pattern...

引用

IEEE Workshop on neural Networks for Signal Processing

作者： R. Kothari K. Agyepong Artificial Neural Systems Laboratory Department of Electrical & Computer Engineering & Computer Science University of Cincinnati Cincinnati OH USA

Additional inputs to a feedforward network, derived from the output of the hidden layer neurons, allow a feedforward network to deal with temporal pattern recognition and reproduction tasks. These 'network derived' or 'context' inputs augment the 'true' inputs to the network and allow the network to retain past information necessary for temporal sequence processing. The choice of which hidden neurons to retain to provide the context inputs is difficult. Use of all the hidden neurons increases the size of the overall network resulting in poorer generalization performance. The problem is complicated due to difficulty in choosing the number of hidden layer neurons in the first place. In this paper, we propose the use of regularization terms in the sum-of-squared error cost function. Assuming the hidden layer neurons are indexed 1,2,...,m, the regularization terms force the differentiation of hidden neurons 1 through m/sub 1/, and m/sub 2/ through m (where 1

关键词： Pattern recognition Neurons Context modeling Delay lines Feedforward systems Training data Laboratories computer science Cost function neural networks

来源：评论

学校读者我要写书评

暂无评论

Self-regulation of model order in feedforward neural networks

Self-regulation of model order in feedforward neural network...

引用

International Conference on neural Networks

作者： R. Kothari K. Agyepong Artificial Neural Systems Laboratory Department of Electrical & Computer Engineering & Computer Science University of Cincinnati Cincinnati OH USA

Despite the presence of theoretical results, the application of feedforward neural networks is hampered by the lack of systematic procedural methods for determining the number of hidden neurons to use. The number of hidden layer neurons determine the order of the neural network model and consequently the generalization performance of the network. This paper puts into perspective the approaches used to address this problem and presents a new paradigm which uses dependent evolution of hidden layer neurons to self-regulate the model order. We show through simulations that despite an abundance of free-parameters (i.e. starting with a larger than necessary network), the proposed paradigm allows for localization of specializing hidden layer neurons with the unspecialized hidden layer neurons behaving similarly. These similarly behaving neurons reduce the model order and allow for the benefits of a smaller sized network. Hints on analytically understanding the behavior are also noted.

关键词： Intelligent networks Feedforward systems neural networks Feedforward neural networks Neurons Artificial neural networks computer networks Biological neural networks Training data Laboratories

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11页 << < 2 3 4 5 6 7 8 9 10 11 > >>

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：