检索结果-内蒙古大学图书馆

Author's reply and revision for time-varying weights

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1997年第3期8卷 813-814页

作者： Lee, KY Department of Electrical Engineering Pennsylvania State University PA USA

来源：评论

学校读者我要写书评

暂无评论

A Multivariable Neural Controller for Automatic Ship Berthing

引用

IEEE Control Systems 1997年第4期17卷 31-45页

作者： Zhang, Yao Hearn, Grant E. Sen, Pratyush Department of Marine Technology University of Newcastle upon Tyne Newcastle uponb Tyne NE17RU United Kingdom

This article describes the development and application of a multivariable neural controller for automatic ship berthing. Following a brief review of various methods employed in automatic ship control, an online trained, backpropagation-based neural network controller is presented. The principal intention is to take advantage of the learning ability of neural networks, and to derive an autonomous neural control algorithm which is independent of the mathematical model of the ship. The proposed neural network controller is designed to adjust its parameters online from a direct evaluation of performance accuracy, thereby eliminating the need for off-line training and a "trainer" associated with supervised control. In addition, the nonlinearity of the rudder and the transfer lag of the propeller have been considered in the system design to increase the realism of the simulation. A series of simulation studies, which include wind disturbances and shallow water effects, have been undertaken to demonstrate the adaptive features and the robust performance of the proposed neural control scheme.

关键词： Automatic control Marine vehicles Neural networks backpropagation algorithms Mathematical model Propellers Programmable control Adaptive control Robust control

来源：评论

学校读者我要写书评

暂无评论

An agent-based approach to induction motor drives control

引用

1997 IEEE International Conference on Intelligent Engineering Systems (INES 97)

作者： Caileanu, C Faculty of Electrical Engineering Gheorghe Asachi Technical University of Iasi Iasi Romania

ISBN: (纸本)0780336275

An agent based approach to induction motor control is proposed in this paper, After a short introduction in intelligent agents (controllers) special attention is given to the learning element, Two main learning paradigms, supervised learning and reinforcement learning are used for the drive to exhibit rational behavior, Artificial neural networks are used to learn different mapping inside the intelligent current controller, Matlab(R) has been used as the simulation environment.

关键词： Induction motor drives Mathematical model Electromagnetic modeling Artificial neural networks Induction motors Supervised learning Computer languages backpropagation algorithms Resonance light scattering Intelligent agent

来源：评论

学校读者我要写书评

暂无评论

A stochastic backpropagation algorithm for training neural networks

A stochastic backpropagation algorithm for training neural n...

引用

International Conference on Information, Communications and Signal Processing

作者： Y.Q. Chen T. Yin H.A. Babri School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore

The popularly used backpropagation algorithm (BP) for training multilayered neural networks is generally slow and prone to getting stuck in local minima. A novel method to improve the performance of the BP by randomising the cost function is proposed. The method is effective in helping the BP algorithm to escape from local minima and therefore improve the convergence and generalization. This is demonstrated on a non-convex pattern recognition problem.

关键词： Stochastic processes backpropagation algorithms Neural networks Cost function Multi-layer neural network Convergence Pattern recognition Feedforward neural networks Entropy Jacobian matrices

来源：评论

学校读者我要写书评

暂无评论

The effects of quantization on the backpropagation learning

The effects of quantization on the backpropagation learning

引用

International Conference on Neural Networks

作者： K. Ikeda A. Suzuki K. Nakayama Department of Elec. Computer Engineering Kanazawa University Kanazawa Japan

The effects of the quantization of the parameters of a learning machine are discussed. The learning coefficient should be as small as possible for a better estimate of parameters. On the other hand, when the parameters are quantized, it should be relatively larger in order to avoid the paralysis of learning originated from the quantization. How to choose the learning coefficient is given in this paper from the statistical point of view.

关键词： Quantization Machine learning Multilayer perceptrons Computer errors Neurons Parameter estimation Circuits Stochastic processes backpropagation algorithms Equations

来源：评论

学校读者我要写书评

暂无评论

A dynamic backpropagation algorithm with application to gain-scheduled aircraft flight control system design

A dynamic backpropagation algorithm with application to gain...

引用

Australian and New Zealand Conference on Intelligent Information Systems

作者： Jianliang Wang Weiqiang Zhang School of EEE Nanyang Technological University Singapore Singapore

ISBN: (纸本)0818682183

The authors introduce a dynamic backpropagation algorithm for continuous-time dynamic neural fuzzy systems, as a generalization of the standard backpropagation algorithm for feedforward neural network systems. The proposed algorithm is applied to the design and training of a fuzzy-gain-scheduler for an aircraft flight control system. The trained control system is tested on a full-fledged six-degree-of-freedom nonlinear aircraft simulation package. Simulation results show that significant improvement is achieved through training of the fuzzy-gain-scheduler by using the proposed dynamic backpropagation algorithm.

关键词： backpropagation algorithms Aerospace control Nonlinear dynamical systems Aircraft Fuzzy systems Neural networks Feedforward neural networks Algorithm design and analysis Control system synthesis Nonlinear control systems

来源：评论

学校读者我要写书评

暂无评论

Combination of adaptive signal processing and neural classification using an extended backpropagation algorithm

Combination of adaptive signal processing and neural classif...

引用

IEEE Workshop on Neural Networks for Signal Processing

作者： A. Doering H. Witte Institute of Medical Statistics Computer Science and Documentation Friedrich-Schiller-Universitat Jena Jena Thuringen Germany

Beside the use of purely neural systems, the combination of preprocessing units and neural classifiers has been used for a variety of signal segmentation and classification tasks. Whereas this approach reduces the input dimensionality as well as the complexity of the classification problem, its performance crucially depends on a proper preprocessing scheme, i.e., feature extraction. In this contribution, adaptive preprocessing units (frequency-selective quadrature filters) are proposed that can be adjusted in order to provide optimal features. The mean frequencies of the filters are tuned to minimize the classification error. Both FIR- and IIR-based filters are introduced and compared with respect to their convergence properties and the classification results. Results for the solution of an EEG segmentation task using the combined system are given.

关键词： Adaptive signal processing Frequency Neural networks Signal processing algorithms Data preprocessing Adaptive filters Electroencephalography Signal processing Robust stability backpropagation algorithms

来源：评论

学校读者我要写书评

暂无评论

Extraction of crisp logical rules using constructive constrained backpropagation networks

Extraction of crisp logical rules using constructive constra...

引用

International Conference on Neural Networks

作者： W. Duch R. Adamczak K. Grabczewski Department of Computer Methods Nicolaus Copernicus University Torun Poland

The problem of extraction of crisp logical rules from neural networks trained with a backpropagation algorithm is solved by smooth transformation of these networks into simpler networks performing logical functions. Two constraints are included in the cost function: a regularization term inducing weight decay, and an additional term forcing the remaining weights to /spl plusmn/1 integer values. Networks with minimal number of connections are created, leading to a small number of crisp logical rules. A constructive algorithm is proposed, in which rules are generated consecutively by adding more nodes to the network. Rules that are most general, covering many training examples, are created first, followed by more specific rules, covering a few cases only. This constructive algorithm applied to the iris classification problem generates two rules with three antecedents giving 98.7% accuracy. A single rule for the mushroom problem leads to 98.52% accuracy while three additional rules allow for perfect classification. The rules found for the three monk problems classify all examples correctly.

关键词： Neural networks Cost function Fuzzy logic Neurons Computer networks Electronic mail backpropagation algorithms Iris Data mining Medical services

来源：评论

学校读者我要写书评

暂无评论

The backpropagation algorithm applied to protective relaying

The backpropagation algorithm applied to protective relaying

引用

International Conference on Neural Networks

作者： D.V. Coury D.C. Jorge Electrical Engineering Department University of São Paulo Sao Paulo Brazil

Distance relays have attracted considerable attention for the protection of transmission lines. They are usually designed on the basis of fixed settings. Therefore, the reach of such relays is affected by the changing network conditions. The implementation of a pattern recognizer for power system diagnosis can provide great advances in the protection field. This paper demonstrates the use of an artificial neural network as a pattern classifier for distance relay operation. The backpropagation algorithm is utilized for the learning process. The scheme utilizes the magnitude of three phase voltage and current phasors as inputs. An improved performance with the use of an artificial neural network approach is experienced once the relay can operate correctly, keeping the reach when faced with different fault conditions as well as network configuration changes.

关键词： backpropagation algorithms Protective relaying Artificial neural networks Power system protection Power system relaying Power transmission lines Transmission line theory Pattern recognition Digital relays Voltage

来源：评论

学校读者我要写书评

暂无评论

On the implementation of backpropagation on the Alex AVX-2 parallel system

On the implementation of backpropagation on the Alex AVX-2 p...

引用

International Conference on Neural Networks

作者： H.M. Abbas M.M. Bayoumi Department of Electrical and Computer Engineering Queen's University Kingston ON Canada

Training backpropagation (BP) networks is a time-consuming process especially on sequential machines. This has motivated the use of parallel architectures to decrease the processing time required for training. In this paper the implementation of the BP algorithm on the Alex AVX-2 MIMD machine is investigated. Due to the high communication time caused by sending and receiving network information and due to the overhead of the message passing process, the conventional use of block-BP is not appropriate for this particular machine. Increasing the processing load of the workers with respect to the communication load will definitely increase the speedup factor. Here, we propose a block-update learning method for BP which reduces the communication time and produces results similar to those obtained with parallel block-BP.

关键词： Message passing Parallel architectures backpropagation algorithms Network topology Master-slave Encoding Learning systems Neural networks Feedforward neural networks Large-scale systems

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：