检索结果-内蒙古大学图书馆

International Conference on Advanced in Control Engineering and Information Science (CEIS)

作者： Jiao Jian Lin Jun Zhou Xiao-hua Lu Hao Jilin Univ Coll Instrumentat & Elect Engn Changchun 130026 Peoples R China

For the standard neural network algorithm has defects such as: local minima and slow convergence rate, etc., an iterative inversion method of neural network Rayleigh wave based the stable and fast levenberge-marquardt (lm) algorithm is put forward. This method increases the network training rate and reduces the times of iterative inversion through numerical optimization and verifies the effectiveness of the method through iterative inversion of the medium model. According to the comparison and analysis, it indicates that the method reduces the times of iterative inversion and increases the convergence rate obviously. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of [CEIS 2011]

关键词： lm algorithm neural network Rayleigh wave iterative inversion

来源：评论

学校读者我要写书评

暂无评论

Inversion of Neural Network Rayleigh Wave Dispersion Based on lm algorithm

引用

Procedia Engineering 2011年 15卷 5126-5132页

作者： JIAO Jian LIN Jun ZHOU Xiao-hua LU Hao College of Instrumentation and Electrical Engineering Jilin UniversityChangchun 130026China

关键词： lm algorithm neural network Rayleigh wave iterative inversion

来源：评论

学校读者我要写书评

暂无评论

Improved extreme learning machine for multivariate time series online sequential prediction

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2015年 40卷 28-36页

作者： Wang, Xinying Han, Min Dalian Univ Technol Fac Elect Informat & Elect Engn Dalian Liaoning Peoples R China

Multivariate time series has attracted increasing attention due to its rich dynamic information of the underlying systems. This paper presents an improved extreme learning machine for online sequential prediction of multivariate time series. The multivariate time series is first phase-space reconstructed to form the input and output samples. Extreme learning machine, which has simple structure and good performance, is used as prediction model. On the basis of the specific network function of extreme learning machine, an improved Levenberg-Marquardt algorithm, in which Hessian matrix and gradient vector are calculated iteratively, is developed to implement online sequential prediction. Finally, simulation results of artificial and real-world multivariate time series are provided to substantiate the effectiveness of the proposed method. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： Online prediction Multivariate time series Extreme Learning Machine lm algorithm

来源：评论

学校读者我要写书评

暂无评论

Calibration Study of Moisture Production Parameters Model Based on Neural Network by lm algorithm

Calibration Study of Moisture Production Parameters Model Ba...

引用

2011 International Conference on New Technology of Agricultural Engineering(ICAE 2011)

作者： Liu Ling1,Zhao Yong-zhi2,Wang Lei3,Wang Yang-ren4 1.Liu Ling Tanjin Agricultural University,hydraulic engineering department,Tianjin,China2.Zhao Yong-zhi Tanjin Agricultural University,hydraulic engineering department,Tianjin,China3.Wang Lei Tanjin Agricultural University,senior profession institute,Tianjin,China4.Wang Yang-ren,Tanjin Agricultural University,hydraulic engineering department,Tianjin,China

The is a kind of effective method of water-saving *** moisture production parameters model provide relationship between the output and the *** article Using improved BP neural network based lm algorithm calibrate Jensen model,and solve moisture sensitivity by test results of winter wheat moisture production parameters in Shanxi Province Xiaohe *** this method to solve moisture sensitivity has higher precision and can provide technical guidance to inadequately irrigation.

关键词： lm algorithm Jensen model moisture sensitivity

来源：评论

学校读者我要写书评

暂无评论

Ultrasonic Parameter Estimation Using the Maximum Likelihood Estimation 4

Ultrasonic Parameter Estimation Using the Maximum Likelihood...

引用

2015 4th International Conference on Electrical Engineering (ICEE)

作者： Laddada, S. Lemlikchi, S. Djelouah, H. Si-Chaib, M. O. Ctr Dev Technol Avancees Baba Hassen 16303 Algeria USTHB Phys Mat Lab Bab Ezzouar Algeria UMB Lab Mecan Solides & Syst Boumerdes Algeria

ISBN: (纸本)9781467366731

The estimation of the backscattered echo was performed using the Maximum Likelihood Estimation (MLE). The backscattered ultrasonic echo is modeled as a nonlinear function of a set of parameters using the Gaussian echo model corrupted with an additive noise. Because of the white Gaussian noise (WGN) assumption, the estimation problem reduces to a least squares estimation. Thus, the nonlinear least square curve fitting with the Levenberg-Marquardt (lm) optimization algorithm was tested in the estimation procedure. The results are compared with existing results from the literature. To improve the goodness of the fit, the multivariate denoising procedure were applied as a preprocessing operation. Then, the efficiency and robustness of the lm algorithm are evaluated for both denoised and noisy signals.

关键词： Ultrasonic echo parameter estimation MLE lm algorithm Multivariate Wavelet Denoising

来源：评论

学校读者我要写书评

暂无评论

Analysis and Synthesis of Coplanar Waveguide-Feed using Multilayer Perceptron Feed Forward Neural Networks 3

Analysis and Synthesis of Coplanar Waveguide-Feed using Mult...

引用

3rd International Conference on Signal Processing Communication and Networking

作者： Gunavathi, N. Sriramkumar, D. Natl Inst Technol Dept Elect & Commun Engn Tiruchirappalli 15 Tamil Nadu India

ISBN: (纸本)9781467368230

Analysis and synthesis of coplanar waveguide feed used in planar antennas have been proposed. Neural network-I has been proposed to analyze the coplanar waveguide feed. It dispenses the use of very long and complex formulae. Neural model-II has been proposed to remove the problems in conventional approach. It synthesizes, even if the dielectric constant is less than 6, unlike the previous approach. It gives the accurate result because thickness of the conductor also is taken into account unlike the conventional approach. The proposed neural networks are trained with three training algorithms like Levenberg-Marquart (lm), Conjugate Gradient of Fletcher-Powell (CGF) and Quasi-Neuron (QN). The lm algorithm is found to be the best algorithms among all based on Mean Squared Error (MSE) values of them.

关键词： analysis CPW feed lm algorithm neural network synthesis

来源：评论

学校读者我要写书评

暂无评论

Learning architectures with enhanced capabilities and easier training 19

Learning architectures with enhanced capabilities and easier...

引用

19th IEEE International Conference on Intelligent Engineering Systems (INES)

作者： Wilamowski, Bogdan M. Korniak, Janusz Auburn Univ Auburn AL 36849 USA Univ Informat Technol & Management Rzeszow Poland

ISBN: (纸本)9781467379397

Although discovery of the Error Back Propagation (EBP) learning algorithm was a real breakthrough, this is not only a very slow algorithm, but it also is not capable of training networks with super compact architecture. The most noticeable progress was done with an adaptation of the lm algorithm to neural network training. The lm algorithm is capable of training networks with 100 to 1000 fewer iterations, but the size of the problems are significantly limited. Also, the lm algorithm was adopted primarily for traditional MLP architectures. More recently two new revolutionary concepts were developed: Support Vector Machine and Extreme Learning Machines. They are very fast, but they train only shallow networks with one hidden layer. It was shown that these shallow networks have very limited capabilities. It has already demonstrated much higher capabilities of super compact architectures having 10 to 100 times more processing power than commonly used learning architectures For example, such a shallow MLP architecture with 10 neurons can solve only a Parity-9 problem, but a special deep FCC (Fully Connected Cascade) architecture with the same 10 neurons can solve as large a problem as a Parity-1023. Unfortunately, with the vanishing gradient problem], deep architectures are very difficult to train. By introducing additional connections across layers it was possible to efficiently train deep networks using the powerful NBN algorithm. Our early results show that there is a solution for this difficult problem.

关键词： backpropagation neural nets support vector machines EBP learning algorithm FCC architecture lm algorithm MLP architecture NBN algorithm error back propagation learning algorithm extreme learning machine fully connected cascade architecture learning architecture neural network training support vector machine Artificial neural networks Biological neural networks Computer architecture FCC Neurons Support vector machines Training Support Vector Network Least mean square algorithm Biological neural networks Neural network back propagation ARCHITECTURE Computer Architecture Federal Communications Commission (FCC) Functional training Learning machines Artificial neural networks Neurons Training

来源：评论

学校读者我要写书评

暂无评论

A FPGA power estimation method based on an improved BP neural network 11

A FPGA power estimation method based on an improved BP neura...

引用

11th International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP)

作者： Zhou, Guochang Guo, Baolong Gao, Xiang Ma, Jing He, Hongjie Yan, Yunyi China Acad Space Technol Xian Xian 710000 Peoples R China Xidian Univ Sch Aerosp Sci & Technol Xian 710071 Peoples R China

ISBN: (纸本)9780769556680

Programmable logic device FPGA has characteristics of flexible design, high efficiency design, short development cycle and low cost. The power of FPGA is divided into static power and dynamic power. The static power is mainly decided by the temperature, it is easy to get power by building a simple model. But the dynamic power is decided by many kinds of design resources. This article focuses on XC4VSX55 FPGA chip and studies the process of its power model, especially proposes a BP neural network algorithm combines adaptive learning rate algorithm with Levenberg-Marquardt. Specific implementation is as follows firstly, gets the sample data provided by XPower Estimator, then trains the sample data by BP neural network, and estimates the intrinsic links through the weights and thresholds of network, finally, obtains the power model. This article provides a power model, and the improved BP network algorithm not only ensures the accuracy of the training results, but also improves the convergence speed.

关键词： FPGA BP neural network XPower Estimator lm algorithm

来源：评论

学校读者我要写书评

暂无评论

Levenberg-Marquardt Training Method for Type-2 Fuzzy Neural Networks and Its Stability Analysis

Levenberg-Marquardt Training Method for Type-2 Fuzzy Neural ...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Khanesar, Mojtaba Ahmadieh Kayacan, Erdal Semnan Univ Fac Elect & Comp Engn Semnan Iran Nanyang Technol Univ Sch Mech & Aerosp Engn Singapore 639798 Singapore

ISBN: (纸本)9781467374286

In this paper, an alternative stability analysis for the Levenberg-Marquardt (lm) algorithm is proposed for the training of Type-2 fuzzy neural networks (T2FNNs). The benefit of the proposed stability analysis is that it does not require any eigenvalues computations, and hence it is simpler when compared to the existing stability analysis studies in literature.

关键词： eigenvalues and eigenfunctions fuzzy neural nets stability lm algorithm Levenberg-Marquardt training method T2FNN alternative stability analysis eigenvalues computation type-2 fuzzy neural network algorithm design and analysis Eigenvalues and eigenfunctions Fuzzy control Fuzzy logic Fuzzy neural networks Stability analysis Training

来源：评论

学校读者我要写书评

暂无评论

A FPGA power estimation method based on an improved BP neural network

A FPGA power estimation method based on an improved BP neura...

引用

International Conference on Intelligent Information Hiding and Multimedia Signal Processing

作者： Guochang Zhou Baolong Guo Xiang Gao Jing Ma Hongjie He Yunyi Yan China Academy of Space Technology (Xi'an) Xi'an 710000 China School of Aerospace Science and Technology Xidian University Xi'an 710071 China

ISBN: (纸本)9781509001897

Programmable logic device FPGA has characteristics of flexible design, high efficiency design, short development cycle and low cost. The power of FPGA is divided into static power and dynamic power. The static power is mainly decided by the temperature, it is easy to get power by building a simple model. But the dynamic power is decided by many kinds of design resources. This article focuses on XC4VSX55 FPGA chip and studies the process of its power model, especially proposes a BP neural network algorithm combines adaptive learning rate algorithm with Levenberg-Marquardt. Specific implementation is as follows, firstly, gets the sample data provided by XPower Estimator, then trains the sample data by BP neural network, and estimates the intrinsic links through the weights and thresholds of network, finally, obtains the power model. This article provides a power model, and the improved BP network algorithm not only ensures the accuracy of the training results, but also improves the convergence speed.

关键词： FPGA BP neural network XPower Estimator lm algorithm

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：