检索结果-内蒙古大学图书馆

IEEE Region 10 Conference (TENCON)

作者： Khadse, Chetan B. Chaudhari, Madhuri A. Borghate, Vijay B. Indian Inst Informat Technol Pune Maharashtra India Visvesvaraya Natl Inst Technol Nagpur Maharashtra India

ISBN: (纸本)9781509011346

In this paper, comparison of seven backpropagation algorithms used in neural network is made for the three phase power quality assessment. Voltage sag and swell are the two disturbances taken into account for comparing the algorithms. These disturbances are generated with the help of programming in MATLAB. The input data, to train the network is the generated sag and swell disturbances. The backpropagation algorithms are taken into account for comparison are conjugate gradient descent, Levenberg-Marquardt, one step secant, Baysian regularization, scaled conjugate gradient descent, gradient descent with momentum and gradient descent with adaptive learning rate. The seven algorithms are used to train the seven networks and tested using simulation model in MATLAB. After testing is done, the comparison is made on the basis of mean squared error, number of neurons, percent of accurate cases detected, number of iterations required for the training process. The testing results for the each algorithm and comparison are presented.

关键词： Training Power quality Neurons Biological neural networks backpropagation algorithms Testing Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Combined Training of Recurrent Neural Networks with Particle Swarm Optimization and backpropagation algorithms for Impedance Identification

Combined Training of Recurrent Neural Networks with Particle...

引用

IEEE Swarm Intelligence Symposium, SIS

作者： Peng Xiao Ganesh K. Venayagamoorthy Keith A. Corzine Department of Electrical and Computer Engineering University of Missouri Rolla USA

A recurrent neural network (RNN) trained with a combination of particle swarm optimization (PSO) and backpropagation (BP) algorithms is proposed in this paper. The network is used as a dynamic system modeling tool to identify the frequency-dependent impedances of power electronic systems such as rectifiers, inverters, and DC-DC converters. As a category of supervised learning methods, the various backpropagation training algorithms developed for recurrent neural networks use gradient descent information to guide their search for optimal weights solutions that minimize the output errors. While they prove to be very robust and effective in training many types of network structures, they suffer from some serious drawbacks such as slow convergence and being trapped at local minima. In this paper, a modified particle swarm optimization technique is used in combination with the backpropagation algorithm to traverse in a much larger search space for the optimal solution. The combined method preserves the advantages of both techniques and avoids their drawbacks. The method is implemented to train a RNN that successfully identifies the impedance characteristics of a three-phase inverter system. The performance of the proposed method is compared to those of both BP and PSO when used separately to solve the problem, demonstrating its superiority

关键词： Recurrent neural networks Particle swarm optimization backpropagation algorithms Impedance Inverters Modeling Frequency conversion Power electronics Rectifiers DC-DC power converters

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

Modified backpropagation algorithms for training the multilayer feedforward neural networks with hard-limiting neurons

Modified backpropagation algorithms for training the multila...

引用

Canadian Conference on Electrical and Computer Engineering (CCECE)

作者： Xiangui Yu N.K. Loh G.A. Jullien W.C. Miller Department of Electrical Engineering University of Windsor Windsor ONT Canada Center for Robotics and Advanced Automation Dodge Hall of Engineering Oakland University Rochester MI USA

This paper introduces modified backpropagation algorithms for training multilayer feedforward neural networks with hard-limiting neurons. Transforming neuron activation functions are used in all the hidden layers, which are the modified continuous sigmoidal functions with an adaptive steepness factors. In the training process, this steepness factor varies from a small positive value to infinite with the decrease of the sum square error. Thus, a multilayer feedforward neural network can be trained with the resultant architecture only composed of hard limiting neurons. The learning algorithm is similar to the conventional backpropagation algorithm. Only the derivatives of the hidden neural activation functions are modified. Extensive numerical simulations are presented to show the feasibility of the proposed algorithm. In addition, the numerical properties of the proposed algorithm are discussed and comparisons of the proposed algorithm with other algorithms are made.< >

关键词： Multi-layer neural network backpropagation algorithms Neural networks Feedforward neural networks Neurons Multilayer perceptrons Very large scale integration Robotics and automation Electronic mail Numerical simulation

来源：评论

学校读者我要写书评

暂无评论

Second-order backpropagation algorithms for a stagewise-partitioned separable Hessian matrix

Second-order backpropagation algorithms for a stagewise-part...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： E. Mizutani S.E. Dreyfus J.W. Demmel Department of Computer Science Tsinghua University Hsinchu Taiwan Industrial Engineering & Operations Research University of California Berkeley Berkeley CA USA Mathematics & Computer Science University of California Berkeley CA USA

Recent advances in computer technology allows the implementation of some important methods that were assigned lower priority in the past due to their computational burdens. Second-order backpropagation (BP) is such a method that computes the exact Hessian matrix of a given objective function. We describe two algorithms for feed-forward neural-network (NN) learning with emphasis on how to organize Hessian elements into a so-called stagewise-partitioned block-arrow matrix form: (1) stagewise BP, an extension of the discrete-time optimal-control stagewise Newton of Dreyfus 1966; and (2) nodewise BP, based on direct implementation of the chain rule for differentiation attributable to Bishop 1992. The former, a more systematic and cost-efficient implementation in both memory and operation, progresses in the same layer-by-layer (i.e., stagewise) fashion as the widely-employed first-order BP computes the gradient vector. We also show intriguing separable structures of each block in the partitioned Hessian, disclosing the rank of blocks.

关键词： backpropagation algorithms Optimal control Computer science Feedforward systems Neural networks Industrial engineering Operations research Mathematics Optimization methods Multi-layer neural network

来源：评论

学校读者我要写书评

暂无评论

Comparison Analysis of Forecasting Accuracy for Electricity Consumption Using Extreme Learning Machine and backpropagation algorithms

Comparison Analysis of Forecasting Accuracy for Electricity ...

引用

Electrical Engineering (FORTEI-ICEE), FORTEI-International Conference on

作者： Nanda Putri Miefthawati Sukma Akbar Zulfatri Aini Sutoyo Department of Electrical Engineering State Islamic University of Sultan Syarif Kasim Riau Pekanbaru Indonesia

ISBN: (数字)9798331542207

ISBN: (纸本)9798331542214

Accurate calculations are essential in forecasting. Therefore, it is important to select the appropriate forecasting method, which can be determined by testing the accuracy level of the forecasting results using the MAPE value. The purpose of this research is to analyze the comparison of the accuracy of electricity consumption forecasts using the Extreme Learning Machine and backpropagation algorithms. The data used are monthly electricity consumption data as input pattern designs. The input data will be divided into two parts: training data and testing data, followed by simulations using the Extreme Learning Machine and backpropagation algorithms to obtain the 2022 forecast results. The accuracy of each algorithm's forecast results will then be calculated using the MAPE value. The research results indicate that the Extreme Learning Machine algorithm has a MAPE value of 4.67%, where the error rate is higher than the backpropagation algorithm, which has only 2.27%. From the algorithm testing stages, the most accurate forecasting result for electricity consumption was obtained using backpropagation, as it has the lowest MAPE value, indicating the highest accuracy and lowest error rate.

关键词： backpropagation Accuracy Extreme learning machines Error analysis Electricity Urban areas Training data backpropagation algorithms Predictive models Forecasting

来源：评论

学校读者我要写书评

暂无评论

Using fast backpropagation algorithms for impulsive noise reduction from highly distorted images

Using fast backpropagation algorithms for impulsive noise re...

引用

Midwest Symposium on Circuits and Systems (MWSCAS)

作者： E. Besdok M. Alci P. Civicioglu Institute of Science Computer Engineering Department Erciyes University Kayseri Turkey Engineering Faculty Electronic Engineering Department Erciyes University Kayseri Turkey

A new impulsive noise elimination filter, which is based on fast backpropagation algorithms, is proposed in this paper. The simulation results show that the proposed filter achieves a superior performance over the other filters mentioned in this paper in the cases of being effective in noise suppression and detail preservation, especially when the noise density is high

关键词： backpropagation algorithms Noise reduction Filters Pixel Artificial neural networks Jacobian matrices Nonlinear distortion Electronic mail Noise generators Intelligent networks

来源：评论

学校读者我要写书评

暂无评论

Predicting the Selling Price of Cars Using Business Intelligence with the Feed-forward backpropagation algorithms

Predicting the Selling Price of Cars Using Business Intellig...

引用

International Conference on Informatics and Computing (ICIC)

作者： Nur Oktavin Idris Aspian Achban Siti Andini Utiarahman Jorry Karim Fuad Pontoiyo Sekolah Tinggi Manajemen Informatika dan Komputer Ichsan Gorontalo Gorontalo Indonesia Universitas Gadjah Mada Yogyakarta Indonesia Universitas Ichsan Gorontalo Gorontalo Indonesia Magister of System Engineering Universitas Gadjah Mada Yogyakarta Indonesia

ISBN: (数字)9781728180472

ISBN: (纸本)9781728180489

The automotive industry is increasingly competitive every year by releasing cars featured with innovative specifications offered by automotive manufacturing companies. The specifications, supported by the technology and performance a car has, are a tool to determine a car's price. However, today the automotive industry frequently releases a new product or type of car with the latest specifications, affecting a car's price to change. It perplexes car manufacturing companies when they are determining a car's price. Responding to this issue, an approach to a decision-making strategy to predict a car's price is needed. One of the approaches that can be implemented is business intelligence with its primary aspects i.e. descriptive, predictive, and prescriptive. Using the concept, we implement Business Intelligence and use the feed-forward backpropagation algorithm to predicts the selling price of a car based on its specification and predict a car price based on the latest specification which has never been on sale. The research findings, identified by using a dataset containing the specifications of BMW, reveal that the actual price and predicted price are close at a mean error of 11.46%. Besides, the research findings also state that the predicted price of a new car with new specifications is $55,754. This research aims to analyze the estimation of the price of a car with the latest specification, which is the focus of the implementation of the business intelligence method we do.

关键词： Industries backpropagation algorithms Companies Manufacturing Automobiles Business intelligence Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

A TRANSIENT LEARNING COMPARISON OF ROSENBLATT, backpropagation, AND LMS algorithms FOR A SINGLE-LAYER PERCEPTRON FOR SYSTEM-IDENTIFICATION

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 1994年第5期42卷 1247-1251页

作者： ENGEL, I BERSHAD, NJ Department of Electrical and Computer Engineering University of California Irvine CA USA

This correspondence presents a transient performance comparison of the Rosenblatt, backpropagation, and LMS training algorithms for a single layer perceptron. The perceptron is attempting to identify a specific nonlinear system with Gaussian inputs. A summary of the first and second moment behaviors of the three algorithms is presented. With the criteria of probability of correct classification versus the number or algorithm iterations, the statistical results are used to compare the learning performance of the algorithms for some specific parameter values. By both the theoretical analysis and by Monte Carlo simulations, it is shown that there are no significant learning performance differences among these three algorithms for these parameter selections.

关键词： Least squares approximation backpropagation algorithms Signal processing algorithms System identification Convergence Nonlinear systems Probability Performance analysis Algorithm design and analysis Adaptive algorithm

来源：评论

学校读者我要写书评

暂无评论

Comparison of particle swarm optimization and backpropagation as training algorithms for neural networks

Comparison of particle swarm optimization and backpropagatio...

引用

IEEE Swarm Intelligence Symposium

作者： Gudise, VG Venayagamoorthy, GK Univ Missouri Dept Elect & Comp Engn Rolla MO 65401 USA

ISBN: (纸本)0780379144

Particle swarm optimization (PSO) motivated by the social behavior of organisms, is a step up to existing evolutionary algorithms for optimization of continuous nonlinear functions. backpropagation (BP) is generally used for neural network training. Choosing a proper algorithm for training a neural network is very important. In this paper, a comparative study is made on the computational requirements of the PSO and BP as training algorithms for neural networks. Results are presented for a feedforward neural network learning a non-linear function and these results show that the feedforward neural network weights converge faster with the PSO than with the BP algorithm.

关键词： Artificial neural networks backpropagation algorithms Computer networks Educational institutions Feedforward neural networks Neural networks Neurons Particle swarm optimization Pattern recognition Venus

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：