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

180 篇 期刊文献
102 篇 会议
3 篇 学位论文

馆藏范围

285 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

244 篇 工学
- 147 篇 计算机科学与技术...
- 85 篇 电气工程
- 33 篇 控制科学与工程
- 20 篇 信息与通信工程
- 18 篇 软件工程
- 13 篇 材料科学与工程（可...
- 13 篇 电子科学与技术（可...
- 12 篇 环境科学与工程（可...
- 10 篇 石油与天然气工程
- 9 篇 土木工程
- 8 篇 机械工程
- 8 篇 仪器科学与技术
- 6 篇 水利工程
- 5 篇 化学工程与技术
- 4 篇 动力工程及工程热...
- 4 篇 交通运输工程
- 3 篇 测绘科学与技术
- 3 篇 核科学与技术
54 篇 理学
- 16 篇 数学
- 12 篇 物理学
- 9 篇 生物学
- 7 篇 统计学（可授理学、...
- 5 篇 化学
- 4 篇 地球物理学
- 3 篇 系统科学
- 3 篇 生态学
32 篇 管理学
- 32 篇 管理科学与工程(可...
18 篇 医学
- 10 篇 基础医学(可授医学...
- 10 篇 临床医学
4 篇 经济学
- 4 篇 应用经济学
4 篇 农学

主题

285 篇 backpropagation ...
48 篇 neural network
36 篇 neural networks
34 篇 artificial neura...
33 篇 artificial neura...
16 篇 multilayer perce...
12 篇 backpropagation
10 篇 classification
9 篇 deep learning
8 篇 pattern recognit...
8 篇 particle swarm o...
7 篇 ann
7 篇 machine learning
6 篇 neural nets
6 篇 genetic algorith...
6 篇 multilayer perce...
5 篇 decision boundar...
5 篇 system identific...
5 篇 on-line learning
5 篇 prediction

机构

4 篇 tijuana inst tec...
2 篇 dept. of compute...
2 篇 himeji inst tech...
2 篇 department of te...
2 篇 kiet dept elect ...
2 篇 indian stat inst...
2 篇 tech univ madrid...
2 篇 raajdhani engn c...
2 篇 directorate of p...
2 篇 natl univ singap...
2 篇 brno university ...
2 篇 pakistan electri...
2 篇 univ aizu dept c...
2 篇 yildiz tech univ...
2 篇 andhra univ coll...
2 篇 bengal engn & sc...
2 篇 fdn fulgor ra-50...
1 篇 worcester polyte...
1 篇 univ milan dept ...
1 篇 zagazig univ fac...

作者

4 篇 gaxiola fernando
4 篇 melin patricia
4 篇 valdez fevrier
3 篇 tanaka h
3 篇 park ys
3 篇 al-andoli mohamm...
3 篇 ishibuchi h
3 篇 castillo oscar
3 篇 zhao qiangfu
3 篇 kaneda yuya
3 篇 liu yong
3 篇 tan shing chiang
2 篇 hueda mario r.
2 篇 qiangfu zhao
2 篇 goh pey yun
2 篇 lek s
2 篇 xie yuquan
2 篇 ollé tamás
2 篇 sivatte-adroer m...
2 篇 hata y

语言

263 篇 英文
19 篇 其他
2 篇 中文
1 篇 德文
1 篇 法文

检索条件"主题词=backpropagation algorithm"

共 285 条记录，以下是201-210 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：

IP Core Based Hardware Implementation of Multi-layer Perceptrons on FPGAs: A Parallel Approach

IP Core Based Hardware Implementation of Multi-layer Percept...

引用

International Conference on Materials Science and Information Technology (MSIT 2011)

作者： Li, Xiaojun Li, Lin S China Univ Technol Sch Mech & Automot Engn Guangzhou Guangdong Peoples R China

ISBN: (纸本)9783037853191

There're many models derived from the famous bio-inspired artificial neural network (ANN). Among them, multi-layer perceptron (MLP) is widely used as a universal function approximator. With the development of EDA and recent research work, we are able to use rapid and convenient method to generate hardware implementation of MLP on FPGAs through pre-designed IP cores. In the mean time, we focus on achieving the inherent parallelism of neural networks. In this paper, we firstly propose the hardware architecture of modular IP cores. Then, a parallel MLP is devised as an example. At last, some conclusions are made.

关键词： Artificial Neural Network (ANN) FPGA hardware implementation backpropagation algorithm IP cores

来源：评论

学校读者我要写书评

暂无评论

On-Line Training with Guide Data: Shall We Select the Guide Data Randomly or Based on Cluster Centers?

On-Line Training with Guide Data: Shall We Select the Guide ...

引用

IEEE Symposium Series on Computational Intelligence (IEEE SSCI)

作者： Kaneda, Yuya Zhao, Qiangfu Liu, Yong Univ Aizu Dept Comp Sci & Engn Aizu Wakamatsu Fukushima Japan

ISBN: (纸本)9781509042401

To retrain an existing multilayer perceptron (MLP) on-line using newly observed data, it is necessary to incorporate the new information while preserving the performance of the network. This is known as the "plasticitystability" problem. For this purpose, we proposed an algorithm for on-line training with guide data (OLTA-GD). OLTA-GD is good for implementation in portable/wearable computing devices (P/WCDs) because of its low computational cost, and can make us more independent of the internet. Results obtained so far show that, in most cases, OLTA-GD can improve an MLP steadily. One question in using OLTA-GD is how we can select the guide data more efficiently. In this paper, we investigate two methods for guide data selection. The first one is to select the guide data randomly from a candidate data set G, and the other is to cluster G first, and select the guide data from G based on the cluster centers. Results show that the two methods do not have significant difference in the sense that both of them can preserve the performance of the MLP well. However, if we consider the risk of "instantaneous performance degradation", random selection is not recommended. In other words, cluster center-based selection can provide more reliable results for the user during on-line training.

关键词： Decision Boundary Making Multilayer Perceptron backpropagation algorithm On-Line Learning Guide Data

来源：评论

学校读者我要写书评

暂无评论

Optimized Neural Network for Improved Electrocardiogram Beat Classification 6

Optimized Neural Network for Improved Electrocardiogram Beat...

引用

IEEE 6th International Advance Computing Conference (IACC)

作者： Dash, Sanjit K. Rao, G. Sasibhushana Raajdhani Engn Coll Dept ECE Bhubaneswar Orissa India Andhra Univ Coll Engn Dept ECE Visakhapatnam Andhra Pradesh India

ISBN: (纸本)9781467382861

The performance of neural network as a classifier depends on several factors such as initialization of weights, its architecture, between class imbalance in the dataset, activation function etc. Though a three layered neural network is able to approximate any non-linear function, number of neurons in the hidden layer plays a significant roll in the performance of the classifier. In this study, the importance of the number of hidden layer neurons of neural network is analyzed for the classification of ECG signals. Five different arrhythmias and the normal beat are classified for different number of hidden layer neurons to examine the performance of the classifier. In this study we get the best number as 35. After the training of the neural network with the optimized number of neurons in the hidden layer, we have tested the performance with three different datasets. The average sensitivity, specificity and accuracy achieved is 94.91%, 99.69% and 99.46% respectively.

关键词： Optimized Artificial Neural Network ECG Arrhythmia Multiclass Pattern Classification backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimization of type-2 Fuzzy Weight for Neural Network using Genetic algorithm and Particle Swarm Optimization

Optimization of type-2 Fuzzy Weight for Neural Network using...

引用

World Congress on Nature and Biologically Inspired Computing (NaBIC)

作者： Gaxiola, Fernando Melin, Patricia Valdez, Fevrier Castillo, Oscar Tijuana Inst Technol Tijuana Mexico

ISBN: (纸本)9781479914159

In this paper two bio-inspired methods are applied to optimize the type-2 fuzzy inference systems used in the neural network with type-2 fuzzy weights. The genetic algorithm and particle swarm optimization are used to optimize the two type-2 fuzzy systems that work in the backpropagation learning method with type-2 fuzzy weight adjustment. The mathematical analysis of the learning method architecture and the adaptation of type-2 fuzzy weights are presented. In this work an optimized type-2 fuzzy inference systems to manage weights for the neural network and the results for the two bio-inspired methods are presented. The proposed approach is applied to a case of time series prediction, specifically in Mackey-Glass time series.

关键词： Neural Networks Type-2 Fuzzy Weights backpropagation algorithm Type-2 fuzzy system

来源：评论

学校读者我要写书评

暂无评论

Use Multilayer Perceptron in Calibrating Multistage Non-linearity of Split Pipelined-ADC

Use Multilayer Perceptron in Calibrating Multistage Non-line...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Zhang, Tianli Cao, Yuefeng Ye, Fan Ren, Junyan Fudan Univ State Key Lab ASIC & Syst Shanghai Peoples R China

ISBN: (纸本)9781538648810

A split-based background calibration technique for pipelined-ADC is proposed in this brief to handle both capacitors' mismatches and non-linearity of residue amplifiers in multiple pipeline stages. Some concepts and approaches of machine learning, say multilayer perceptron and backpropagation algorithm, are introduced to deal with the problems appearing in modeling and solving the nonlinear calibration filter. Computer simulations demonstrate an exaltation of both SNDR and SFDR for more than 50dB in a 15-bit 7-stages pipelined-ADC with non-ideal first three stages.

关键词： pipelined ADC background calibration split ADC machine learning multilayer perceptron backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Modification of Learning Feedforward Neural Networks with the BP Method 20th

Modification of Learning Feedforward Neural Networks with th...

引用

20th International Conference on Artificial Intelligence and Soft Computing (ICAISC)

作者： Bilski, Jaroslaw Smolag, Jacek Najgebauer, Patryk Czestochowa Tech Univ Dept Comp Engn Al Armii Krajowej 36 PL-42200 Czestochowa Poland

ISBN: (纸本)9783030879860;9783030879853

The backpropagation (BP) algorithm is a worldwide used method for learning neural networks. The BP has a low computational load. Unfortunately, this method converges relatively slowly. In this paper a new approach to the backpropagation algorithm is presented. The proposed solution speeds up the BP method by using vector calculations. This modification of the BP algorithm was tested on a few standard examples. The obtained performance of both methods was compared.

关键词： Feedforward neural network Neural network learning algorithm backpropagation algorithm Parallel computation

来源：评论

学校读者我要写书评

暂无评论

Testing Artificial Metaplasticity in MLP Applications

Testing Artificial Metaplasticity in MLP Applications

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Andina, Diego Marcano-Cedeno, Alexis Torres, Joaquin Alarcon, Martin J. Tech Univ Madrid UPM Grp Automat Signals & Commun Madrid Spain

ISBN: (纸本)9781424427932

In this work we tested and compared Artificial Metaplasticity (AMP) results for Multilayer Perceptrons (MLPs). AMP is a novel Artificial Neural Network (ANN) training algorithm inspired on the biological metaplasticity property of neurons and Shannon's information theory. During training phase, AMP training algorithm gives more relevance to less frequent patterns and subtracts relevance to the frequent ones, claiming to achieve a much more efficient training, while at least maintaining the MLP performance. AMP is specially recommended when few patterns are available to train the network. We implement an Artificial Metaplasticity MLP (AMMLP) on standard and well-used databases for Machine Learning. Experimental results show the superiority of AMMLPs when compared with recent results on the same databases.

关键词： Neural Network MLPs backpropagation algorithm Pattern Recognition Metaplasticity

来源：评论

学校读者我要写书评

暂无评论

Neural Network & Genetic algorithm Based Approach to Network Intrusion Detection & Comparative Analysis of Performance

Neural Network & Genetic Algorithm Based Approach to Network...

引用

15th International Conference on Computer and Information Technology (ICCIT)

作者： Pal, Biprodip Hasan, Md. Al Mehedi Rajshahi Univ Engn & Technol Dept Comp Sci & Engn Rajshahi Bangladesh

ISBN: (纸本)9781467348362;9781467348331

In this paper backpropagation learning algorithm and genetic algorithm is applied for network intrusion detection and also to classify the detected attacks into proper types. During the training process of the backpropagation algorithm two possible set of features in the rule sets are used separately to determine proper rule set features for better performance. Then the performance of genetic algorithm is compared to the performance of both of the backpropagation approach. The process is tested on training dataset as well as test dataset to analyze the performance. It is found that in detecting the attack connections backpropagation algorithm shows better performance but in classifying the detected attacks into proper types the genetic algorithm approach is more successful.

关键词： backpropagation algorithm Genetic algorithm Intrusion detection Security

来源：评论

学校读者我要写书评

暂无评论

Inclined Planes Optimization algorithm in Optimal Architecture of MLP Neural Networks 3

Inclined Planes Optimization Algorithm in Optimal Architectu...

引用

3rd International Conference on Pattern Analysis and Image Analysis (IPRIA)

作者： Shahraki, Najmeh Sayyadi Zahiri, Seyed-Hamid Univ Birjand Dept Elect & Comp Engn Birjand Iran

ISBN: (纸本)9781509064540

In this paper an Inclined Planes Optimization algorithm, is used to optimize the performance of the multilayer perceptron. Indeed, the performance of the neural network depends on its parameters such as the number of neurons in the hidden layer and the connection weights. So far, most research has been done in the field of training the neural network. In this paper, a new algorithm optimization is presented in optimal architecture for data classification. Neural network training is done by backpropagation (BP) algorithm and optimization the architecture of neural network is considered as independent variables in the algorithm. The results in three classification problems have shown that a neural network resulting from these methods have low complexity and high accuracy when compared with results of Particle Swarm Optimization and Gravitational Search algorithm.

关键词： Inclined Planes Optimization algorithm the architecture of neural network classification backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Networks Model to Improve the Performance Index of the Coil-Disc Assembly in Tube Flow 1st

Artificial Neural Networks Model to Improve the Performance ...

引用

1st International Conference on Computational Intelligence and Informatics (ICCII)

作者： Durga, R. Kanaka Kumar, C. Srinivasa Mohan, Vaka Murali Kumar, L. Praveen Prasad, P. Rajendra VIGNAN Inst Technol Sci Dept CSE Hyderabad TS India TRR Coll Engn Dept CSE Hyderabad TS India Andhra Univ AUCE Dept Chem Engn Visakhapatnam AP India

ISBN: (纸本)9789811024719;9789811024702

An artificial neural networks model to enhance the performance index of mass transfer function in tube flow by means of entry region coil-disc assembly promoter was inserted coaxially is presented in this paper. Popular backpropagation algorithm was utilized to test, train and normalize the network data to envisage the performance of mass transfer function. The experimental data of the study is separated into two sets one is training sets and second one is validation sets. The 248 sets of the experimental data were used in training and 106 sets for the validation of the artificial neural networks using MATLAB 7.7.0, particularly tool boxes to predict the performance index of the mass transfer in tube for faster convergence and accuracy. The weights were initialized within the range of [-1, 1]. The network limitations in all attempts taken learning rate as 0.10 and momentum term as 0.30. The finest model was selected based on the MSE, STD and R2. In this, network with 5_8_1 configuration is recommended for mass transfer training. This research work reveals that artificial neural networks with adding more number of layers and nodes in hidden layer may not increase the performance of mass transfer function.

关键词： Artificial neural network Mass transfer Coil-disc assembly Tube backpropagation algorithm

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29页 << < 17 18 19 20 21 22 23 24 25 26 > >>

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：