检索结果-内蒙古大学图书馆

APPLICATION OF A MAXIMUM-LIKELIHOOD ESTIMATOR IN AN EXPERIMENTAL-STUDY IN ULTRASONIC DIFFRACTION TOMOGRAPHY

IEEE TRANSACTIONS ON MEDICAL IMAGING 1993年第3期12卷 545-554页

作者： TSIHRINTZIS, GA DEVANEY, AJ NORTHEASTERN UNIV DEPT ELECT & COMP ENGNBOSTONMA 02115 AJ DEVANEY ASSOCIATES INC BOSTONMA 02116

We evaluate a recently proposed approach [1]-[3] to the inverse problem of detection of the presence and estimation of the location of a known object from data collected in a set of diffraction tomographic experiments. We verify on experimental data the validity of the filtered backpropagation algorithms developed in [1]-[3], demonstrate their robustness to modeling errors and to severe limitations in the angular coverage of the tomographic data, and illustrate a potential application in medical imaging of soft tissue.

关键词： Maximum likelihood estimation Tomography Maximum likelihood detection Inverse problems Object detection Diffraction backpropagation algorithms Robustness Biomedical imaging Biological tissues

来源：评论

学校读者我要写书评

暂无评论

On stochastic approximation algorithms for classes of PAC learning problems

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 1997年第3期27卷 516-522页

作者： Rao, NSV Uppuluri, VRR Oblow, EM Center for Engineering SystemsAdvanced Research Oak Ridge National Laboratory Oak Ridge TN USA

The classical stochastic approximation methods are shown to yield algorithms to solve several formulations of the PAC learning problem defined on the domain [0,1](d). Under some smoothness conditions on the probability measure functions, simple algorithms to solve some PAC learning problems are proposed based on networks of nonpolynomial units (e.g. artificial neural networks). Conditions on the sizes of the samples required to ensure the error bounds are derived using martingale inequalities.

关键词： Stochastic processes Approximation algorithms backpropagation algorithms Artificial neural networks Neural networks Approximation methods Risk management Pattern recognition Concrete Power engineering and energy

来源：评论

学校读者我要写书评

暂无评论

AN ACCELERATED LEARNING ALGORITHM FOR MULTILAYER PERCEPTRON NETWORKS

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1994年第3期5卷 493-497页

作者： PARLOS, AG FERNANDEZ, B ATIYA, AF MUTHUSAMI, J TSAI, WK TEXAS A&M UNIV DEPT NUCL MEDCOLLEGE STNTX 77843 UNIV TEXAS DEPT MECH ENGNAUSTINTX 78712 CAIRO UNIV DEPT ELECT ENGNCAIROEGYPT UNIV CALIF IRVINE DEPT ELECT & COMP ENGNIRVINECA 92717

An accelerated learning algorithm (ABP-adaptive back propagation1) is proposed for the supervised training of multilayer perceptron networks. The learning algorithm is inspired from the principle of ''forced dynamics'' for the total error functional. The algorithm updates the weights in the direction of steepest descent, but with a learning rate a specific function of the error and of the error gradient norm. This specific form of this function is chosen such as to accelerate convergence. Furthermore, ABP introduces no additional ''tuning'' parameters found in variants of the backpropagation algorithm. Simulation results indicate a superior convergence speed for analog problems only, as compared to other competing methods, as well as reduced sensitivity to algorithm step size parameter variations.

关键词： Acceleration Multilayer perceptrons Convergence backpropagation algorithms Force control Error correction Nonlinear control systems Control systems Force feedback Nonlinear dynamical systems

来源：评论

学校读者我要写书评

暂无评论

PERFORMANCE EVALUATION OF MULTILAYER PERCEPTRONS IN SIGNAL-DETECTION AND CLASSIFICATION

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第2期6卷 381-386页

作者： MICHALOPOULOU, ZH NOLTE, LW ALEXANDROU, D DUKE UNIV DEPT ELECT ENGNDURHAMNC 27706

Multilayer perceptrons trained with the backpropagation algorithm are tested in detection and classification tasks and are compared to optimal algorithms resulting from likelihood ratio tests. The focus is on the problem of one of M orthogonal signals in a Gaussian noise environment, since both the Bayesian detector and classifier are known for this problem and can provide a measure for the performance evaluation of the neural networks. Two basic situations are considered: detection and classification. For the detection part, it was observed that for the signal-known-exactly case (M = 1) the performance of the neural detector converges to the performance of the ideal Bayesian decision processor, while for a higher degree of uncertainty (i.e., for a larger M) the performance of the multilayer perceptron is inferior to that of the optimal detector. For the classification case the probability of error of the neural network is comparable to the minimum Bayesian error, which can be numerically calculated. Adding noise during the training stage of the network does not affect the performance of the neural detector;however, there is an indication that the presence of noise in the learning process of the neural classifier results in a degraded classification performance.

关键词： Multilayer perceptrons Detectors Bayesian methods backpropagation algorithms Testing Neural networks Gaussian noise Noise measurement Signal processing Uncertainty

来源：评论

学校读者我要写书评

暂无评论

LEARNING WITHOUT LOCAL MINIMA IN RADIAL BASIS FUNCTION NETWORKS

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第3期6卷 749-756页

作者： BIANCHINI, M FRASCONI, P GORI, M Dipartimento di Sistemi e Informatica Università di Firenze Italy

Learning from examples plays a central role in artificial neural networks. The success of many learning schemes is not guaranteed, however, since algorithms like backpropagation may get stuck in local minima, thus providing suboptimal solutions. For feedforward networks, the theoretical results reported in [5], [6], [15], and [20] show that optimal learning can be achieved provided that certain conditions on the network and the learning environment are met. A similar investigation is put forward in this paper for the case of networks using radial basis functions (RBF) [10], [14]. The analysis proposed in [6] is extended naturally under the assumption that the patterns of the learning environment are separable by hyperspheres. In that case, we prove that the attached cost function is local minima free with respect to all the weights. This provides us with some theoretical foundations for a massive application of RBF in pattern recognition.

关键词： Intelligent networks Radial basis function networks Pattern recognition Cost function Neural networks Pattern analysis Rough surfaces Surface roughness backpropagation algorithms Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Neural network learning of low-probability events

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 1996年第3期32卷 898-910页

作者： Munro, DJ Ersoy, OK Bell, MR Sadowsky, JS PURDUE UNIV SCH ELECT ENGNW LAFAYETTEIN 47907

In the problem of stationary target identification (STI) via millimeter wave (MMW) seeker radars in heavy clutter environments, it is often necessary to use nonparametric identification procedures, as detailed parametric models of clutter and target returns are generally unavailable. Neural networks provide an attractive approach to perform nonparametric identification However, when identifying low-probability events, the computational overhead associated with training a neural network can become excessive. This is because low-probability events must be adequately represented in the training sample. We present a modified backpropagation training algorithm based on a likelihood ratio weighting function (LRWF) to train the neural network using a much smaller training set than that required using the standard backpropagation algorithm. This algorithm is closely related to the importance sampling technique used in digital communication system to obtain probability of error estimates by using a much smaller number of simulation runs than what is required with standard Monte Carlo simulation The modified backpropagation technique results in a significant reduction in computational overhead in training the network, resulting from a substantial reduction in the size of the training set required to achieve a given level of performance. We demonstrate the performance of the algorithm on simulated data for the STI problem in MMW radar.

关键词： Neural networks backpropagation algorithms Millimeter wave radar Computer networks Communication standards Computational modeling Millimeter wave communication Millimeter wave technology Radar clutter Parametric statistics

来源：评论

学校读者我要写书评

暂无评论

On-line adaptive control of non-linear plants using neural networks with application to liquid level control

引用

INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING 1998年第1期12卷 13-28页

作者： Ng, GW Cook, PA Univ Manchester Inst Sci & Technol Dept EEE Control Syst Ctr Manchester M60 1QD Lancs England

In this paper, we present two on-line adaptive control algorithms for non-linear plants using neural networks. The architecture used is based on the concept of specialized learning, which was first proposed by Psaltis et al.(4) and suffers from two main problems, namely lack of knowledge of the plant Jacobian and slow training speed if the standard backpropagation algorithm is used. Specialized learning has been tested successfully by several researchers using the sign of the plant Jacobian, chosen on the basis of prior qualitative knowledge of the plant. It has also been proposed to calculate the plant Jacobian through a pretrained model. However, if off-line training of the model is not possible and qualitative knowledge of the plant Jacobian is not available, then specialised learning may not be feasible for an on-line neurocontroller. We propose that it is possible to estimate the plant Jacobian through the model on-line for a slowly varying plant. Some analysis for calculating the plant Jacobian on-line is discussed. For rapidly varying plant, we propose using the recursive least-squares (RLS) training algorithm instead of the standard back-propagation (BP) algorithm in the specialised learning architecture. We show that RLS training is faster than the BP algorithm. The proposed fast algorithm is then tested on simulated non-linear plants as well as in a real-time application to a coupled-tanks test rig. (C) 1998 John Whey & Sons, Ltd.

关键词： Distress network applications Neural network adaptive control backpropagation algorithms Liquid level control knowledge IN-LINE level control Jacobian

来源：评论

学校读者我要写书评

暂无评论

On-line training of recurrent neural networks with continuous topology adaptation

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1996年第1期7卷 222-228页

作者： Obradovic, D Corporate Research and Development Siemens AG Munich Germany

This paper presents a novel on-line procedure for training dynamic neural networks with input-output recurrences whose topology is continuously adjusted to the complexity of the target system dynamics. The latter is accomplished by changing the number of the elements of the network hidden layer whenever the existing topology cannot capture the dynamics presented by the new data. The training mechanism developed in this work is based on the suitably altered extended Kalman filter (EKF) algorithm which is simultaneously used for the network parameter adjustment and for its state estimation. The network itself consists of a single hidden layer with a Gaussian radial basis functions (GRBF's) and of a linear output layer. The choice of the GRBF is induced by the requirements of the online learning. The latter implies the network architecture which permits only local influence of the new data point in order not to forget the previously learned dynamics. The continuous topology adaptation is implemented in our algorithm to avoid memory and computational problems of using a regular grid of GRBF's which covers the network input space. Furthermore, we show that the resulting parameter increase can be handled ''smoothly'' without interfering with the already acquired information. In the case when the target system dynamics are changing over time, we show that a suitable forgetting factor can he used to ''unlearn'' the no-longer-relevant dynamics. The quality of the presented recurrent network training algorithm is demonstrated on the identification of nonlinear dynamic systems.

关键词： Recurrent neural networks Network topology State estimation Nonlinear dynamical systems Feedback loop Neural networks backpropagation algorithms Computer architecture Computer networks Grid computing

来源：评论

学校读者我要写书评

暂无评论

A fast multilayer neural-network training algorithm based on the layer-by-layer optimizing procedures

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1996年第3期7卷 768-775页

作者： Wang, GJ Chen, CC Department of Mechanical Engineering National Chung Hsing University Taichung Taiwan

A faster new learning algorithm to adjust the weights of the multilayer feedforward neural network is proposed, In this new algorithm, the weight matrix (W-2) of the output layer and the output vector (Y) of the previous layer are treated as two variable sets. An optimal solution pair (W-2*, Y-P*) is found to minimize the sum-square-error of the patterns input, Y-P* is then used as the desired output of the previous layer, The optimal weight matrix and layer output vector of the hidden layers in the network is found with the same method as that used for the output layer, In addition, the dynamic forgetting factors method makes the proposed new algorithm even more powerful in dynamic system identification, Computer simulation shows that the new algorithm outmatches other learning algorithms both in converging speed and in computation time required.

关键词： Nonhomogeneous media Multi-layer neural network Neural networks Convergence Feedforward neural networks backpropagation algorithms System identification Computer simulation Robustness Power system modeling

来源：评论

学校读者我要写书评

暂无评论

AN ARTIFICIAL NEURAL NETWORK FOR SPECT IMAGE-RECONSTRUCTION

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 1991年第3期10卷 485-487页

作者： FLOYD, CE DUKE UNIV DEPT BIOMED ENGNDURHAMNC 27710

An artificial neural network has been developed to reconstruct quantitative single photon emission computed tomographic (SPECT) images. The network is trained with an ideal projection-image pair to learn a shift-invariant weighting (filter) for the projections. Once trained, the network produces weighted projections as a hidden layer when acquired projection data are presented to its input. This hidden layer is then backprojected to form an image as the network output. The learning algorithm adjusts the weighting coefficients using an algorithm (backpropagation) which minimizes the mean squared error between the ideal training image and the reconstructed training image. In the language of neural networks, this is a two-layer network with one hiden layer (the weighted projection) whose weights are trained using backpropagation with supervised training and a modified delta rule. The response of the trained network to an impulse projection resembles the ramp filter typically used with backprojection and reconstructed images are similar to filtered backprojection images. This encouraging result indicates that this artificial neural network architecture may be useful for investigating the tomographic reconstruction process.

关键词： Artificial neural networks Image reconstruction Biological neural networks Computer networks Filters Single photon emission computed tomography Optical computing backpropagation algorithms Cognition Decision making

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：