检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

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

The backpropagation algorithm is a very popular approach to learning in feed-forward multi-layer perceptron networks. However, in many scenarios the time required to adequately learn the task is considerable. Many existing approaches have improved the convergence rate by altering the learning algorithm. We present a simple alternative approach inspired by opposition-based learning that simultaneously considers each network transfer function and its opposite. The effect is an improvement in convergence rate and over traditional backpropagation learning with momentum. We use four common benchmark problems to illustrate the improvement in convergence time.

关键词： Convergence Transfer functions Neural networks backpropagation algorithms Genetic algorithms Pattern analysis Machine intelligence Laboratories System analysis and design Design engineering

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

INFERENCE OF OIL CONTENT IN PETROLEUM WAXES BY ARTIFICIAL NEURAL NETWORKS

引用

IFAC Proceedings Volumes 2006年第2期39卷 759-764页

作者： Anie D.M. Lima Danilo do C.S. Silva Valéria S. Silva De Souza B. Maurício Research And Development Center (CENPES) Lubricants and Special Products PETROBRAS Rio de Janeiro Brazil School of Chemistry Federal University of Rio de Janeiro (UFRJ) Rio de Janeiro Brazil

The reduction of the time required to determine oil content is important in the production of petroleum waxes. Here, it is aimed to generate a model whose output (the inferred oil content) is obtained from inputs given by other characterization parameters (needle penetration, viscosity, density and refractive index) that are obtained from simpler experiments. Laboratory experiment data together with industrial data were employed in the modeling. These ‘real’ data were compared with predictions made by the linear models and artificial neural networks. The networks outperform the linear models, as they generate smaller residuals in the whole operational range considered.

关键词： Nonlinear analysis system Artificial intelligence Process parameter estimation Product quality Neural-network models backpropagation algorithms

来源：评论

学校读者我要写书评

暂无评论

Estimating Snow Water Equivalent from Satellite Passive and Active Microwave Sensors

Estimating Snow Water Equivalent from Satellite Passive and ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： M. Brogioni G. Macelloni S. Paloscia P. Pampaloni S. Pettinato E. Santi CNR-IFAC Florence Italy

来源：评论

学校读者我要写书评

暂无评论

Wavenet Based Modeling of Vehicle Suspension System

Wavenet Based Modeling of Vehicle Suspension System

引用

Annual Conference of Industrial Electronics Society

作者： Yul Y. Nazaruddin Yuliati Department of Engineering Physics Institut Teknologi Bandung Bandung Indonesia Electrical Engineering Department Widya Mandala Surabaya Catholic University Surabaya Indonesia

An alternative modeling technique of vehicle suspension system which is based on an integration between wavelet theory and artificial neural network, or wavelet network (wavenet) is presented. Wavenet is a single hidden layer feedforward neural network, which uses wavelet basis function as an activation function. Polynomial windowed with Gaussian (POLYWOG) will be applied as the basis function. Wavenet parameters, such as weight, dilation and translation of the wavelet function will be optimized during its learning process, which is performed by a backpropagation algorithm. For minimizing the mean square error between model outputs and its observation, an iterative minimization method of gradient steepest descent is applied. Experimental evaluation of the proposed technique has been conducted using an input-output data collected from a running test vehicle. Observations by comparing the model responses with the actual output measurements revealed that satisfactory model matching were obtained which means that the models have captured the real basic features of the vehicle suspension dynamic characteristics

关键词： Vehicles Artificial neural networks Neural networks Feedforward neural networks Polynomials backpropagation algorithms Mean square error methods Iterative methods Minimization methods Testing

来源：评论

学校读者我要写书评

暂无评论

Combining Gradient and Evolutionary Approaches to the Artificial Neural Networks Training According to Principles of Support Vector Machines

Combining Gradient and Evolutionary Approaches to the Artifi...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： M. Bundzel P. Sincak Department of Cybernetics and Artificial Intelligence Technical University of Košice Letna Slovakia

A gradient based learning for ANN training in pattern recognition tasks and a genetic approach for ANN pruning are proposed in this paper. The goal is to achieve a wide margin classifier the Vapnik-Chevornenkis (VC) dimension of which is being reduced in order to increase the generalization performance. Inspired by Support Vector Machines the examples closest to the decision boundary contribute to the training the most. The training penalty is rule-based and calculated according to the spatial distribution of the training examples relative to the separating hyperplane. The tendency to saturation of hidden neurons is suppressed. Genetic algorithm based method is proposed for reduction of the size of a trained ANN. The proposed algorithms were tested on artificial and real world data and compared to standard backpropagation and Support Vector Machine with Gaussian RBF kernel.

关键词： Artificial neural networks Support vector machines Support vector machine classification Pattern recognition Virtual colonoscopy Neurons Genetic algorithms backpropagation algorithms Testing Kernel

来源：评论

学校读者我要写书评

暂无评论

Robust Pruning of RBF Network for Neural Tracking Control Systems

Robust Pruning of RBF Network for Neural Tracking Control Sy...

引用

IEEE Conference on Decision and Control

作者： Jie Ni Qing Song M.J. Grimble School of Electrical and Electronic Engineering Nanyang Technological University Singapore Department of Electronic and Electrical Engineering University of Strathclyde UK

ISBN: (纸本)9781424401703

It is difficult to determine the number of nodes that should be used in a neural network. An adaptive method is proposed whereby the initial select is based on the largest expected number and the algorithm then "prunes" the numbers. A robust backpropagation training algorithm is proposed for the online tuning of a radial basis function(RBF) network tracking control system. The structure of the RBF network controller is derived using a filtered error approach. The proposed pruning method in this paper begins with a relatively large network, and certain neural units of the RBF network are dropped by examining the estimation error increment. A complete convergence proof is provided in the presence of disturbances

关键词： Robust control Radial basis function networks Control systems Neural networks backpropagation algorithms Convergence Error correction Multi-layer neural network Multilayer perceptrons System testing

来源：评论

学校读者我要写书评

暂无评论

Short-Term System Marginal Price Forecasting Using System-Type Neural Network Architecture

Short-Term System Marginal Price Forecasting Using System-Ty...

引用

IEEE PES Power Systems Conference and Exposition, PSCE

作者： Byounghee Kim John P. Velas Jeongkyu Lee Jongbae Park Joongrin Shin Kwang Y. Lee Electrical Engineering Department Pennsylvania State University University Park PA USA Electrical Engineering Department Konkuk University Seoul South Korea

Neural networks have been applied in various new ways to the problem of short-term load and electricity price forecasting for power systems. Virtually all of these methods are based on using statistical patterns, which are perceived between the yearly load and system marginal price (SMP) histories of the system to predict the forecasted year's power demand and SMP. The SMP forecasting is a very important element in an electricity market for the optimal biddings of market participants as well as for market stabilization of regulatory bodies. The proposed method introduces a system type neural network architecture to perform electricity price forecasting. Specifically, the proposed approach begins with the premise that the electricity price for a given year can be given a structure which can then be related to the structure of the reference year, in such a way that a transformation can be found from the reference year's structure to the forecasting year's structure. The transformation depends upon how parameters, which influenced the SMP but can not be measured, move from the reference year to the forecasting year

关键词： Neural networks Economic forecasting Load forecasting Power systems Electricity supply industry Artificial neural networks backpropagation algorithms Power system dynamics Power markets Power generation

来源：评论

学校读者我要写书评

暂无评论

A Novel BP Algorithm Based on Self-adaptive Parameters and Performance Analysis

A Novel BP Algorithm Based on Self-adaptive Parameters and P...

引用

International Conference on Innovative Computing, Information and Control (ICICIC)

作者： Haibin Cai Liangxu Liu Qiying Cao College of Information Science and Technology Donghua Uinversity Shanghai China

The standard back-propagation(BP) algorithm converges slowly and is easy to trap into local minimum, which is the main reason why it cannot be used widely in practical applications. Therefore, a new BP algorithm based on self-adaptive parameters, called the SAPBP algorithm for short, is put forward in this paper. The convergence stability is enhanced by adding the positive matrix in Hessian matrix. The SAPBP algorithm is used in approximating nonlinear function in order to test its performance. The data of simulation experiment have proved that the improved algorithm can converges very fast and avoid trapping into local minimum. The convergence stability, also, is very good. The results demonstrate the proposed scheme is efficient, and has good performance

关键词： Performance analysis Function approximation Error correction Algorithm design and analysis Educational institutions Convergence Stability Testing backpropagation algorithms Neurons

来源：评论

学校读者我要写书评

暂无评论

A new on-line self-constructing neural fuzzy network

A new on-line self-constructing neural fuzzy network

引用

IEEE Conference on Decision and Control

作者： Andres Ferreyra Jose de Jesus Rubio Departamento de Electrónica Sección de Intrumentación Universidad Autonoma Metropolitana Azcapotzalco Mexicali Mexico Departamento de Electrónica Sección de Intrumentación México D.F. México

ISBN: (纸本)1424401704;9781424401703

In this paper, we propose a new on-line self-constructing neural fuzzy network. Structure and parameter learning are updated at the same time in our algorithm, because there is no difference between them. It generates groups with a given radius. The center is updated in order to get a nearest one to the incoming data in each iteration, in this way, it does not generate many rules and it does not need to prune them. We give a time varying learning rate for backpropagation training. We use extended Kalman filter to train the center of sets in the THEN part. We proved the stability in both cases

关键词： Fuzzy neural networks Fuzzy control Stability Fuzzy logic Nonlinear systems Least squares methods backpropagation algorithms Input variables Fuzzy sets Optimization methods

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：