检索结果-内蒙古大学图书馆

A ROBUST BACK-PROPAGATION LEARNING ALGORITHM FOR FUNCTION APPROXIMATION

IEEE TRANSACTIONS ON NEURAL NETWORKS 1994年第3期5卷 467-479页

作者： CHEN, DS JAIN, RC UNIV MICHIGAN DEPT ELECT ENGN & COMP SCIARTIFICIAL INTELLIGENCE LABANN ARBORMI 48109

The back propagation (BP) algorithm allows multilayer feedforward neural networks to learn input-output mappings from training samples. Due to the nonlinear modeling power of such networks, the learned mapping may interpolate all the training points. When erroneous training data are employed, the learned mapping can oscillate badly between data points. In this paper we derive a robust BP learning algorithm that is resistant to the noise effects and is capable of rejecting gross errors during the approximation process. The spirit of this algorithm comes from the pioneering work in robust statistics by Huber an d Hampel. Our work is different from that of M-estimators in two aspects: 1) the shape of the objective function changes with the iteration time;2) the parametric form of the functional approximator is no longer linear: it is a nonlinear cascade of affine transformations. In contrast to the conventional BP algorithm, three advantages of the robust BP algorithm are: 1) it approximates an underlying mapping rather than interpolating training samples;2) it is robust against gross errors;3) its rate of convergence is improved since the influence of incorrect samples is gracefully suppressed.

关键词： backpropagation algorithms Multi-layer neural network Noise robustness Neural networks Feedforward neural networks Training data Approximation algorithms Noise shaping Parametric statistics Shape

来源：评论

学校读者我要写书评

暂无评论

A MULTIPLE TIME-SCALE MODULARIZED ADAPTIVE BEAMFORMER

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 1994年第5期42卷 1251-1256页

作者： NIEZGODA, GH KROLIK, JL DUKE UNIV DEPT ELECT ENGNDURHAMNC 27708

This paper analyzes the cascaded equivalent form of the minimum variance distortionless response (MVDR) beamformer. A unique feature of the modularized MVDR (M2VDR) beamformer is the ability to distribute adaptive degrees of freedom (DOF) among beamformer stages. This property of the M2VDR beamformer allows DOF to be adapted over different time scales. As a consequence of the multiple stage decomposition adaptive beamformer weights appear in a form which suggest an apparent increase in the number of DOF. To properly analyze this case an alternative interpretation of adaptive DOF is introduced to establish the equivalence between the MVDR beamformer and its cascaded realization. In the second part of this paper the distribution for the output power estimate of a P stage M2VDR beamformer is derived. Analysis reveals the necessity of placing constraints on the adaptation time assigned to each beamformer stage. Simulation experiments are presented that demonstrate the applicability of the M2VDR beamformer in resolving closely spaced sources under impulsive interference conditions.

关键词： Signal processing algorithms backpropagation algorithms Least squares approximation Classification algorithms Neural networks Adaptive signal processing Algorithm design and analysis System identification Speech processing Acoustic distortion

来源：评论

学校读者我要写书评

暂无评论

SELF-TUNING OF COMPUTED TORQUE GAINS BY USING NEURAL NETWORKS WITH FLEXIBLE STRUCTURES

引用

IEE PROCEEDINGS-CONTROL THEORY AND APPLICATIONS 1994年第4期141卷 235-242页

作者： TESHNEHLAB, M WATANABE, K SAGA UNIV FAC SCI & ENGNDEPT MECH ENGNSAGA 840JAPAN

The paper principally describes the design of an artificial neural network using flexible sigmoid unit functions (FSUFs), referred to as flexible sigmoid function networks (FSFNs), to achieve both a high flexibility and a high learning ability in neural network structures from a given set of teaching patterns. An FSFN can generate an appropriate shape of the sigmoid function for each of the individual hidden- and output-layer units, in accordance with the specified inputs, desired output(s) and applied system. The paper proposes a learning method in which not only connection weights but also the sigmoid functions may be adjusted. The learning algorithm is derived by using the well known back-propagation algorithm. To demonstrate the validity of the proposed method, we apply the FSFN to the construction of a self-tuning computed torque controller for a two-link manipulator. It is then shown that the controller based on the FSFN gives a better control performance than that based on the traditional neural network.

关键词： backpropagation algorithms COMPUTED TORQUE CONTROL FLEXIBLE SIGMOID FUNCTIONS NEURAL NETWORKS SELF-TUNING CONTROL

来源：评论

学校读者我要写书评

暂无评论

TRAINING FULLY RECURRENT NEURAL NETWORKS WITH COMPLEX WEIGHTS

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING 1994年第3期41卷 235-238页

作者： KECHRIOTIS, G MANOLAKOS, ES Center for Communications and Digital Signal Processing (CDSP) Research and Graduate Studies Electrical and Computer Engineering Department Northeastern University Boston MA USA

In this brief paper, the Real Time Recurrent Learning (RTRL) algorithm for training fully recurrent neural networks in real time, is extended for the case of a recurrent neural network whose inputs, outputs, weights and activation functions are complex. A practical definition of the complex activation function is adopted and the complex form of the conventional RTRL algorithm is derived. The performance of the proposed algorithm is demonstrated with an application in complex communication channel equalization.

关键词： Recurrent neural networks Signal processing algorithms Communication channels Neural networks backpropagation algorithms State-space methods Limit-cycles Speech processing Adaptive equalizers Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

TRAINING FEEDFORWARD NETWORKS WITH THE MARQUARDT ALGORITHM

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1994年第6期5卷 989-993页

作者： HAGAN, MT MENHAJ, MB

The Marquardt algorithm for nonlinear least squares is presented and is incorporated into the backpropagation algorithm for training feedforward neural networks. The algorithm is tested on several function approximation problems, and is compared with a conjugate gradient algorithm and a variable learning rate algorithm. It is found that the Marquardt algorithm is much more efficient than either of the-other techniques when the network contains no more than a few hundred weights.

关键词： feedforward network function approximation algorithms backpropagation algorithms feedforward neural nets Nonlinear least squares conjugate gradient learning rate

来源：评论

学校读者我要写书评

暂无评论

A HYBRID ALGORITHM FOR DETERMINING PROTEIN-STRUCTURE

引用

IEEE EXPERT-INTELLIGENT SYSTEMS & THEIR APPLICATIONS 1994年第4期9卷 66-74页

作者： ZYHANG, X One Cambridge Center PHZ Partners Cambridge MA

At Thinking Machines, my colleagues and I have developed a hybrid system combining a neural network, a statistical module, and a memory-based reasoner, each of which makes its own prediction. A combiner then blends these results to produce the final predictions. This hybrid system improves its ability to determine how amino acid sequences fold into 3D protein structures. It predicts secondary structures with 66.4% accuracy. Both the neural network and the combiner are multilayer perceptrons trained with the standard backpropagation algorithm; this article focuses on the other two components, and on how we trained the hybrid system and used it for prediction. I also discuss how future work in AI and other sciences might meet the challenge of the protein folding problem.

关键词： Proteins Neural networks Amino acids Multi-layer neural network Multilayer perceptrons backpropagation algorithms Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A DYNAMIC LEARNING NEURAL-NETWORK FOR REMOTE-SENSING APPLICATIONS

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 1994年第5期32卷 1096-1102页

作者： TZENG, YC CHEN, KS KAO, WL FUNG, AK UNIV TEXAS WAVE SCATTERING RES CTRARLINGTONTX 76019

The neural network learning process is to adjust the network weighs to adapt the selected training data. Based on the polynomial basis function (PBF) modeled neural network that is a modified multilayer perceptrons (MLP) network, a dynamic learning algorithm (DL) is proposed in this paper. The presented learning algorithm makes use of Kalman filtering technique to update the network weights, in the sense that the stochastic characteristics of incoming data sets are implicitly incorporated into the network. The Kalman gains which represent the learning rates of the network weights updating are calculated by using the U-D factorization. By concatenating all of the network weights at each layer to form a long vector such that it can be updated without propagating back, the proposed algorithm improves the performance of convergence to which the back-propagation (BP) learning algorithm often suffers. Numerical illustrations are carried out using two categories of problems: multispectral imagery classification and surface parameters inversion. Results indicates the use of Kalman filtering algorithm not only substantially increases the convergence rate in the learning stage, but also enhances the separability for highly nonlinear boundaries problems, as compared to BP algorithm, suggesting that the proposed DL neural network provides a practical and potential tool for remote sensing applications.

关键词： Neural networks Remote sensing Filtering algorithms Kalman filters backpropagation algorithms Convergence Training data Polynomials Multi-layer neural network Multilayer perceptrons

来源：评论

学校读者我要写书评

暂无评论

Comments on "Comparative analysis of backpropagation and the extended Kalman filter for training multilayer perceptrons"

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 1994年第8期16卷 862-863页

作者： P. Sarat Chandran Centre for Signal Processing School of Electrical and Electronic Engineering Nanyang Technological University Singapore

In this note, the connection between the backpropagation algorithm and the extended Kalman filter is analyzed using an alternate form of representation for the Kalman gain term and shown to be much simpler than that r... 详细信息

关键词： Multi-layer neural network Kalman filters backpropagation algorithms Neural networks Equations Covariance matrix Algorithm design and analysis State estimation Nonhomogeneous media Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

A suggestion for solving negative transfer problem in VLSI backpropagation neural networks

A suggestion for solving negative transfer problem in VLSI b...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jien-Chung Lo S. Kolluri Department of Electrical Engineering University of Rhode Island Kingston RI USA

To overcome negative transfer problem in backpropagation (BP) neural networks, a modified BP algorithm has been proposed. However, for VLSI BP neural networks, this means an extensive design efforts. We analyze in this paper the nature of negative transfer problem and identify a simple technique to solve the negative transfer problem in VLSI BP neural networks.< >

关键词： Intelligent networks Very large scale integration Neural networks backpropagation algorithms Neurons Histograms Gaussian distribution Performance analysis Algorithm design and analysis Network-on-a-chip

来源：评论

学校读者我要写书评

暂无评论

The manifold backpropagation algorithm

The manifold backpropagation algorithm

引用

International Joint Conference on Neural Networks (IJCNN)

作者： S. Puechmorel M.I. Iahla F. Castanie ENSEEIHT GAPSE Toulouse France Ecole Nationale Superieure d'Electrotechnique d'Electronic d'Informatique d'Hydraulique et des Telecommunications Toulouse Midi-PyrÃ©nÃ©es FR ENSEEIHT Toulouse France

This paper introduces a generalization of the concept of neural network by allowing the activation functions to be defined from a C/sup k/-manifold to a C/sup k/-manifold. Real-valued neural networks (RNN), complex-valued neural networks (CNN) as well as the recently introduced vector neural networks (VNN) can be seen as special cases of manifold neural networks (MNN). The classical back-propagation algorithm can be extended to manifolds, assuming some hypothesis on the order of differentiability and on some global properties of the manifold, The case of analytic manifolds are briefly discussed as well as the case of manifolds with boundaries.< >

关键词： backpropagation algorithms Neural networks Vectors Recurrent neural networks Cellular neural networks Neurons Function approximation Multi-layer neural network Algorithm design and analysis Adaptive filters

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：