检索结果-内蒙古大学图书馆

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： N.J. Bershad J.J. Shynk Electrical and Computer Engineering Department University of California Irvine CA USA Center for Information Processing Research Department of Electrical and Computer Engineering University of California Santa Barbara CA USA

The stationary points of a two-layer perceptron which attempts to identify the parameters of a specific nonlinear system are studied. The training sequence is modeled as the binary output of the nonlinear system when the input is an independent sequence of zero-mean Gaussian vectors with independent components. The training rule backpropagates the error at the input to the outer layer nonlinearity rather than the error at the output of that nonlinearity. Coupled nonlinear equations are derived for the hidden and output layer weights. These equations define a multiplicity of stationary points. One solution to these equations indicates that the hidden layer weights match those of the nonlinear system and that the outer layer weights minimize the MSE. The second layer output can be made to match the training sequence by the appropriate choice of bias. Hence, the two-layer perceptron correctly identifies the parameters of the unknown system even though the training rule does not propagate the output error.< >

关键词： Stochastic systems Convergence Algorithm design and analysis backpropagation algorithms Nonlinear systems Nonlinear equations Multilayer perceptrons Laboratories Couplings Error correction

来源：评论

学校读者我要写书评

暂无评论

The autoregressive backpropagation algorithm

The autoregressive backpropagation algorithm

引用

International Joint Conference on Neural Networks (IJCNN)

作者： R.R. Leighton B.C. Conrath MITRE Corporation McLean VA USA

Describes an extension to error backpropagation that allows the nodes in a neural network to encode state information in an autoregressive 'memory'. This neural model gives such networks the ability to learn to recognize sequences and context-sensitive patterns. Building upon the work of A. Wieland (1990) concerning nodes with a single feedback connection, the authors generalize the method to n feedback connections and address stability issues. The learning algorithm is derived, and a few applications are presented.< >

关键词： backpropagation algorithms Neurofeedback Neurons Stability Output feedback Delay Digital filters Difference equations Neural networks Context modeling

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Case Study on Application of backpropagation Network Using Procedural & Object-Oriented Approach

An Analysis of Case Study on Application of Backpropagation ...

引用

Emerging Innovations and Advanced Computing (INNOCOMP), International Conference on

作者： Alankrita Aggarwal Pardeep Singh Sonali Gupta Computer Science Engineering Department (AIT) Chandigarh University Mohali India SCSE Galgotias University Greater Noida India Deaprtment of CSE Graphic Era Hill University Research Scholor Graphic Era Deemed to be Univeristy Dehradun India

ISBN: (数字)9798350376470

ISBN: (纸本)9798350376487

The backpropagation (BPN) algorithm is used in artificial neural networks (ANN) for training the networks that uses unsupervised learning and it is performed in two consecutive phases for the training. In the first phase, a pattern is provided as input of network and in response to that activities are performed layers-to-layers on inner layers till a response pattern is generated at the output layer. The second phase basically compares the response pattern generated with the input pattern provided and finds the mismatch that occurred. These mismatches for the target values define the error values and are backpropagated to the input layer as feedback. On the basis of this feedback, the weights for inner layers are adjusted again and again in a loop of backpropagation, such that the final error can be minimized. This work has compared and contrasted the recent behavior between training neural networks using the backpropagation algorithm using a structured & object-oriented approach.

关键词： Training backpropagation Technological innovation Artificial neural networks backpropagation algorithms Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

An adaptive backpropagation through time training algorithm for a neutral controller

An adaptive backpropagation through time training algorithm ...

引用

IEEE International Symposium on Intelligent Control (ISIC)

作者： M. Chow S.O. Yee Department of Electrical and Computer Engineering North Carolina State University Raleigh NC USA

An adaptive method is proposed for choosing the time length (or number of time steps) used in the standard backpropagation through time (BTT) algorithm. BTT is commonly used in training neurocontrollers to perform control actions for a given cost function. Traditionally, the time length of BTT is chosen based on experience, and sometimes unnecessary calculations are performed because the time length is too large or too small. The adaptive backpropagation through time (ABTT) algorithm proposed is a technique for finding a minimum time length required to train a controller successfully to achieve its objective using the BTT algorithm. A DC motor controller is used as an example to demonstrate its feasibility. The performance of adaptive and standard BTT is compared in terms of objective achievement, cost function and computation requirements.< >

关键词： Programmable control Adaptive control backpropagation algorithms Cost function Control systems Neurocontrollers DC motors Artificial neural networks IEEE members Computer networks

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

Self-organizing neural networks by dynamic and spatial changing weights 4

Self-organizing neural networks by dynamic and spatial chang...

引用

4th International Symposium on Uncertainty Modeling and Analysis

作者： Homma, N Gupta, MM Yoshizawa, M Abe, K Tohoku Univ Coll Med Sci Aoba Ku Sendai Miyagi 9808575 Japan

ISBN: (纸本)0769519970

We propose a self-organizing neural structure with dynamic and spatial changing weights for forming a feature space representation of concepts. An essential core of this self-organization is an appropriate combination of an unsupervised learning with incomplete information for the dynamic changing and an extended Hebbian rule for a signal-driven spatial changing. A concept formation problem requires the neural network to acquire the complete feature space structure of concept information using an incomplete observation of the concept. The informational structure can be stored as the connection structure of self-organizing network by using the two rules: The Hebbian rule can create a necessary connection, while unsupervised learning can delete unnecessary connections. Finally concept formation ability of the proposed neural network is proven under some conditions.

关键词： backpropagation algorithms Biological neural networks Biomedical engineering Cognition Educational institutions Hebbian theory Learning systems Neural networks Self-organizing networks Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A neural network-based direct inverse control for active control of vibrations of mechanical systems 6

A neural network-based direct inverse control for active con...

引用

6th Brazilian Symposium on Neural Networks

作者： de Abreu, GLCM Teixeira, RL Ribeiro, JF Univ Fed Uberlandia Dep Engn Mecan Lab Dinam Sistemas Mecanicos BR-38400902 Uberlandia MG Brazil

ISBN: (纸本)0769508561

This paper describes the use of Artificial Neural Networks for the control of vibrations of a mechanical system using its experimental direct inverse model. The neural controller is trained to model the experimental inverse model of the plans using the back-propagation algorithm with si, annealing. The inverse nlodel of the plant is obtained by the training mechanism that rises experimental input and output data. After the training the neural network is used as a forward controller. The efficiency and the robustness of the controller are shown through experimental rests. The neural control algorithm is implemented in a computer and the performance of controller is evaluated under a set of experimental tests, made to the active control of vibrations of a mechanical system of orle degree of freedom actuated by magnetic actuators.

关键词： Artificial neural networks backpropagation algorithms Control systems Inverse problems Mechanical systems Neural networks Robust control Simulated annealing Testing Vibration control

来源：评论

学校读者我要写书评

暂无评论

Standardization of Neural Network Terminology

引用

IEEE Transactions on Neural Networks 1990年第2期1卷 244-245页

作者： Eberhart, Russell C. Applied Physics Laboratory Johns Hopkins University Laurel MD 20707 United States

It is desirable to move toward commonly accepted terminology in the neural network field. This letter outlines the initial activities of an Ad Hoc Standards Committee established by the IEEE Neural Networks Council to... 详细信息

关键词： Standardization Neural networks Terminology backpropagation algorithms Control systems Intelligent robots Robot control Knowledge based systems Adaptive control Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Supervised backpropagation neural networks for the classification of ultrasonic signals from fiber microcracking in metal matrix composites

Supervised backpropagation neural networks for the classific...

引用

IEEE Symposium (IUS) Ultrasonics

作者： L.L. Mann T.E. Matikas P. Karpur S. Krishnamurthy NDE Branch Materials Directorate OH USA Research Institute University of Dayton Dayton OH USA Universal Energy Systems Inc. Dayton OH USA

The results of the application of supervised backpropagation neural networks to the classification of ultrasonic signals obtained from a model metal matrix composite are presented. This composite is made of a single fiber embedded in a Ti-24Al-llNb matrix and is used for the characterization of the fiber-matrix interface. The neural network is implemented in the frequency domain with two hidden layers and shows excellent discrimination capability when the network is trained with a judicious choice for the training set of ultrasonic signals. The sensitivity of the performance of the network to the number of examples used for training and the robustness of the algorithm to the change in the training set are discussed.< >

关键词： Neural networks Optical fiber testing backpropagation algorithms Composite materials Inorganic materials Titanium alloys Signal processing Image processing Aerospace materials System testing

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of backpropagation Algorithm of Artificial Neural Networks in Verilog

Performance analysis of Backpropagation Algorithm of Artific...

引用

IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)

作者： J Amrutha A S Remya Ajai Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (数字)9781538624401

ISBN: (纸本)9781538624418

Artificial neural networks learn or get trained to execute definite tasks, instead of programmed computational systems through training algorithms such as backpropagation algorithm. It is the basic tool for pattern classification application of ANN in field of medical diagnosis and remote sensing. This method involves changing the weights in the network using a training set of input output examples. Digital implementation of these neural networks for classification is suitable as it preserves the parallel architecture of the neurons and can be reconfigured by the user with FPGA. This parallelism in neural networks make it potentially fast for computation of tasks. This work implements backpropagation training algorithm in verilog with Modelsim-Altera 6.5b for a feedforward neural network. Since multiplier algorithms determine the operational speed and power consumption; a performance analysis is made based on different multipliers. The work can be further extended to the implementation of artificial neural networks on FPGA and to implement a classification application in the trained network.

关键词： Artificial neural networks Neurons Training Biological neural networks Field programmable gate arrays backpropagation algorithms backpropagation

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：