检索结果-内蒙古大学图书馆

Improving the back-propagation algorithm using evolutionary strategy

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2007年第2期54卷 171-175页

作者： Siu, Sammy Yang, Sheng-Sung Lee, Chien-Min Ho, Chia-Lu Chunghwa Telecom Co Ltd Telecom Labs Tao Yuan 326 Taiwan Natl Cent Univ Inst Elect Engn Chungli 32054 Taiwan Ind Technol Res Inst Informat & Commun Res Labs New Mobile Access Dept Hsinchu 310 Taiwan Natl Cent Univ Inst Commun Engn Chungli 32054 Taiwan

In order to overcome the existence of the local minimum in the multilayer perceptron (MLP) implemented with back-propagation (BP) algorithm, the evolutionary strategy (ES) is proposed. Introducing the factors of the chromosome and gene mutation rates, one can enhance the flexibility of the mutation. The bounds of the chromosome and gene mutation rates are derived. Simulation results are shown to verify the theoretical calculations and also suggest appropriate strategy parameter values. The theoretical results are studied using the MLP-based decision feedback equalizer (MLP DFE) scenarios. The results indicate that the evolutionary strategy outperforms the BP algorithm.

关键词： Genetic mutations Biological cells backpropagation algorithms Multilayer perceptrons Decision feedback equalizers Telecommunications Robustness Laboratories Communication industry Mobile communication

来源：评论

学校读者我要写书评

暂无评论

Three term backpropagation algorithm for classification problem

Three term backpropagation algorithm for classification prob...

引用

作者： Shamsuddin, Siti Mariyam Darus, Maslina Saman, Fadhlina Izzah Soft Computing Research Group Faculty of Computer Science and Information System Universiti Teknologi Malaysia Universiti Kebangsaan Malaysia

Standard backpropagation Algorithm (BP) usually utilizes two term parameters;Learning Rate and Momentum Factor β. Despite the general success of this algorithm, there are several drawbacks such as existence of local minima, slow rates of convergence and modification of algorithm requires complex computations. In this study, further analysis of proportional factor (γ) for 3-Term BP is investigated on various scales of datasets;small, medium and large. Experiments are conducted using three UCI dataset;Balloon, Iris and Cancer. The results show that the 3-Term BP outperforms standard BP for small scale data, but does not work well for medium and large scale dataset. © ICS AS CR 2007.

关键词： backpropagation algorithms

来源：评论

学校读者我要写书评

暂无评论

Convergence of Gradient Descent Algorithm for Diagonal Recurrent Neural Networks

Convergence of Gradient Descent Algorithm for Diagonal Recur...

引用

2nd International Conference on Bio-Inspired Computing

作者： Xu, Dongpo Li, Zhengxue Wu, Wei Ding, Xiaoshuai Qu, Di Dalian Univ Technol Dept Appl Math Dalian 116024 Peoples R China

ISBN: (纸本)9781424441051

Recurrent neural networks have been used for analysis and prediction of time series. This paper is concerned with the convergence of the gradient descent algorithm for training the diagonal recurrent neural networks. The existing convergence results consider the online gradient training algorithm based on the assumption that a very large number of (or infinitely many in theory) training samples of the time series are available, and accordingly the stochastic process theory is used to establish some convergence results of probability nature. In this paper, we consider the case that only a small number of training samples of the time series are available such that the stochastic treatment of the problem is no longer appropriate. Instead, we use the offline gradient descent algorithm for training the diagonal recurrent neural network, and we accordingly prove some convergence results of deterministic nature. The monotonicity of the error function in the iteration is also guaranteed.

关键词： Convergence Recurrent neural networks Neurons Neural networks Stochastic processes Time series analysis backpropagation algorithms Mathematics Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Generalized MLP/BP-based MIMO DFEs for overcoming ISI and ACI in band-limited channels

Generalized MLP/BP-based MIMO DFEs for overcoming ISI and AC...

引用

International Symposium on VLSI Design, Automation and Test

作者： Hsu, Terng-Ren Chen, Chi-Shi Hsu, Terng-Yin Lee, Chen-Yi Natl Chiao Tung Univ Dept Elect Engn 1001 Univ Rd Hsinchu 300 Taiwan Chung Hua Univ Dept Microelect Engn Hsinchu 300 Taiwan Natl Chip Implementat Ctr Natl Appl Res Lab Hsinchu 300 Taiwan Natl Chiao Tung Univ Dept Comp Sci & Informat Engn Hsinchu 300 Taiwan

ISBN: (纸本)9781424405824

in this work, we base on generalized multi-layered perceptron neural networks with backpropagation algorithm (Generalized MLP/BP) to construct multi-input multi-output (MIMO) decision feedback equalizers (DFEs). The proposal is used to recover distorted nonretum-to-zero (NRZ) data in wireline parallel bandlimited channels. From the simulations, we note that the proposed design can recover severe distorted NRZ data as well as suppress intersymbol interference (ISI), adjacent channel interference (ACI) and background noise. The better BER performance as compared to a set of LMS DFEs and an MLPIBP-based MIMO DFE is achieved in the wireline parallel band-limited channels where the data rate is ten times as much as the channel bandwidth.

关键词： Automatic car identification channel bandwidth backpropagation algorithms Data transfer rates bit error rate performance BACKGROUND NOISE

来源：评论

学校读者我要写书评

暂无评论

The comparison and selection about the improving backpropagation algorithms of the neural networks based on MATLAB language

The comparison and selection about the improving backpropaga...

引用

World Congress on Intelligent Control and Automation (WCICA)

作者： Xiangjun Gao Xinzheng Zhang Zhongjuan Li College of Automation Guang Dong University of Technology Guangzhou China

All kinds of modified BP algorithms in the MATLAB's neural networks toolbox are discussed in the optimization techniques and compared with speed and memory. Different problem types applied to those algorithms are ... 详细信息

ISBN: (纸本)0780382730

关键词： backpropagation algorithms Neural networks MATLAB Educational institutions Automation

来源：评论

学校读者我要写书评

暂无评论

A margin maximization training algorithm for BP network

A margin maximization training algorithm for BP network

引用

4th International Symposium on Neural Networks (ISNN 2007)

作者： Wang, Kai Wang, Qingren Nankai Univ Inst Machine Intelligence Tianjin 300071 Peoples R China

ISBN: (纸本)9783540723929

Generalization problem is a key problem in NN society, which can be grouped into two classes: the generalization problem with unlimited size of training sample and that with limited size of training sample. The generalization problem with limited size of training sample is considered in this paper. Similar to margin maximization criterion in SVM, we propose a margin maximization training algorithm for BP network to further improve the generalization ability of BP network. Experimental results show that the margin maximization training algorithm proposed in this paper does improve the performance of BP network, and shows a comparable performance with SVM.

关键词： backpropagation algorithms

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Two Distributed backpropagation Implementations

Performance Evaluation of Two Distributed BackPropagation Im...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Sorin Babii Vladimir Cretu Emil M. Petriu Department of Computers Politehnica University of Timişoara Timisoara Romania School of Information Technology and Engineering University of Ottawa Ottawa ONT Canada

This article 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 two strategies 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

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.

来源：评论

学校读者我要写书评

暂无评论

Opposite Transfer Functions and backpropagation Through Time

Opposite Transfer Functions and Backpropagation Through Time

引用

IEEE Symposium on Foundations of Computational Intelligence, FOCI

作者： Mario Ventresca Hamid R. Tizhoosh Pattern Analysis and Machine Intelligence (PAMI) laboratory Systems Design Engineering Department University of Waterloo Waterloo ONT Canada

backpropagation through time is a very popular discrete-time recurrent neural network training algorithm. However, the computational time associated with the learning process to achieve high accuracy is high. While many approaches have been proposed that alter the learning algorithm, this paper presents a computationally inexpensive method based on the concept of opposite transfer functions to improve learning in the backpropagation through time algorithm. Specifically, we will show an improvement in the accuracy, stability as well as an acceleration in learning time. We will utilize three common benchmarks to provide experimental evidence of the improvements

关键词： Transfer functions backpropagation algorithms Signal processing algorithms Recurrent neural networks Acceleration Convergence Computational intelligence Stability Nonlinear dynamical systems Computational complexity

来源：评论

学校读者我要写书评

暂无评论

A Constructive Approach of Modified Standard backpropagation Algorithm with Optimum Initialization for Feedforward Neural Networks

A Constructive Approach of Modified Standard Backpropagation...

引用

International Conference on Computational Intelligence and Multimedia Applications

作者： N. Gunaseeli N. Karthikeyan Department of MCA K.L.N College of Engineering Department of MCA Madurai Kamaraj University India

For the learning process of multilayer feedforward neural network, the constructive approach of Modified backpropagation algorithm (MBP), with optimum initialization is proposed. One of the common complaints about the Standard backpropagation algorithm (SBP) is that it is very slow. Even simple problems may take hundreds of iterations to converge. SBP algorithm reduces only non-linear errors. Much work, therefore has been done in search of faster methods. One of such approach is modified form of the Standard backpropagation algorithm. Modified backpropagation algorithm consists of minimizing the sum of the squares of linear and non- linear errors for all output units. This leads to an efficient process in the network. Proper initialization always plays a key role in the robust neural networks. Therefore, the optimum initialization method is used for weight initialization, which ensures the outputs of neurons are in the active region and the range of activation function is fully utilized. Since the proposed method uses the constructive approach, there is no need to make a prior estimate of the correct network size. The proposed method is implemented on 2 bit parity problem, 4 bit parity checker and encoder problem and produced good results.

关键词： backpropagation algorithms Neural networks Feedforward neural networks Multi-layer neural network Robustness Neurons Convergence Computational intelligence Educational institutions Pediatrics

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：