检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Yuan-Hsiang Chang Bin Zheng Xiao-Hui Wang W.F. Good Department of Radiology University of Pittsburgh Pittsburgh PA USA University of Pittsburgh Pittsburgh PA US

The authors investigated computer-aided diagnosis (CAD) schemes to determine the probability for the presence of breast cancer using artificial neural networks (ANNs) that were trained by a backpropagation (BP) algorithm or by a genetic algorithm (GA). A clinical database of 418 previously verified patient cases was employed and randomly partitioned into two independent sets for CAD training and testing. During training, the BP and the GA were independently applied to optimize, or to evolve the inter-connecting weights of the ANNs. Both the BP/GA-trained CAD performances were then compared using the receiver-operating characteristics (ROC) analysis. In the training set, both the BP/GA-trained CAD schemes yielded the areas under ROC curves of 0.91 and 0.93, respectively. In the testing set, both the BP/GA-trained ANNs yielded the areas under ROC curves of approximately 0.83. These results demonstrated that the GA performed slightly better, although not significantly, than BP for the training of the CAD schemes.

关键词： Computer aided diagnosis Breast cancer Artificial neural networks Genetic algorithms Testing Biomedical imaging Medical diagnostic imaging Neural networks backpropagation algorithms Databases

来源：评论

学校读者我要写书评

暂无评论

ACL-adaptive correction of learning parameters for backpropagation based algorithms

ACL-adaptive correction of learning parameters for backpropa...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： J. Wilk E. Wilk H. Gobel University of Federal Armed Forces Munich Hamburg Germany University of Applied Sciences Hamburg Hamburg Germany

We present an improvement of backpropagation learning (BP) for Sigma-Pi networks with adaptive correction of the learning parameters (ACL). An improvement of convergency is achieved by using the information value, change of the output error and the validity of Funahashi's theorem to analytically determine values for the learning parameters momentum, learning rate and learning motivation in each learning step. Its application to a neural-network based approximation of continuous input-output mappings with high accuracy yields very good results: the number of training periods of ACL BP learning is smaller than the corresponding number of training periods using other BP based learning rules.

关键词： Equations Approximation error Adaptive systems backpropagation algorithms Neural networks Multi-layer neural network Neurons Least squares methods

来源：评论

学校读者我要写书评

暂无评论

Comparison of particle swarm optimization and backpropagation as training algorithms for neural networks

Comparison of particle swarm optimization and backpropagatio...

引用

IEEE Swarm Intelligence Symposium, SIS

作者： V.G. Gudise G.K. Venayagamoorthy Department of Electrical and Computer Engineering University of Missouri Rolla USA

Particle swarm optimization (PSO) motivated by the social behavior of organisms, is a step up to existing evolutionary algorithms for optimization of continuous nonlinear functions. backpropagation (BP) is generally used for neural network training. Choosing a proper algorithm for training a neural network is very important. In this paper, a comparative study is made on the computational requirements of the PSO and BP as training algorithms for neural networks. Results are presented for a feedforward neural network learning a nonlinear function and these results show that the feedforward neural network weights converge faster with the PSO than with the BP algorithm.

关键词： Particle swarm optimization backpropagation algorithms Neural networks Feedforward neural networks Artificial neural networks Computer networks Pattern recognition Educational institutions Neurons Venus

来源：评论

学校读者我要写书评

暂无评论

Comparison between backpropagation and RPROP algorithms applied to fault classification in transmission lines

Comparison between backpropagation and RPROP algorithms appl...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： B.A. Souza N.S.D. Brito W.L.A. Neves K.M. Silva R.B.V. Lima S.S.B. da Silva Department of Electrical Engineering Federal University of Campina Grande Campina Grande Brazil Companhia Hidroelétrica do São Francisco DPA/DOEM/CHESF Recife Brazil

The computed results from implemented artificial intelligence algorithms, used to identify and classify faults in transmission lines, are discussed in this paper. The proposed methodology uses sampled data of voltage and current waveforms obtained from analog channels of digital fault recorders (DFRs) installed in the field to monitor transmission lines. The performances of resilient propagation (RPROP) and backpropagation algorithms, implemented in batch mode, are addressed for single, double and three-phase fault types.

关键词： backpropagation algorithms Transmission lines Artificial neural networks Power transmission lines Monitoring Fault diagnosis Electronic mail Artificial intelligence Voltage Performance analysis

来源：评论

学校读者我要写书评

暂无评论

A COMPUTATIONAL STUDY OF RECONSTRUCTION algorithms FOR DIFFRACTION TOMOGRAPHY - INTERPOLATION VERSUS FILTERED backpropagation

引用

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING 1983年第5期31卷 1262-1275页

作者： PAN, SX KAK, AC BEIJING INST AERONAUT & ASTRONAUT BEIJINGPEOPLES R CHINA

From the standpoint of reporting a new contribution, this paper shows that by using bilinear interpolation followed by direct two-dimensional Fourier inversion, one can obtain reconstructions of quality which is comparable to that produced by the filtered-backpropagation algorithm proposed recently by Devaney. For an N × N image reconstructed from N diffracted projections, the former approach requires approximately 4N FFT's, whereas the backpropagation technique requires approximately N 2 FFT's. We have also taken this opportunity to present the reader with a tutorial introduction to diffraction tomography, an area that is becoming increasingly important not only in medical imaging, but also in underwater and seismic mapping with microwaves and sound. The main feature of the tutorial part is the statement of the Fourier diffraction projection theorem, which is an extension of the traditional Fourier slice theorem to the case of image formation with diffracting illumination.

关键词： Reconstruction algorithms Tomography Interpolation Image reconstruction backpropagation algorithms Acoustic diffraction Biomedical imaging Lighting

来源：评论

学校读者我要写书评

暂无评论

Should backpropagation be replaced by more effective optimization algorithms?

Should backpropagation be replaced by more effective optimiz...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： J.T. Hsiung W. Suewatanakul D.M. Himmelblau Department of Chemical Engineering University of Technology Austin TX USA

The authors propose the use of backpropagation (BP) as the preferred technique of optimizing the values of the weights in an artificial neural network. They compare functional representation via BP and a successive quadratic programming code, with the latter being at least four times faster in achieving the same error tolerance. The proposed strategy has two main features. One is that it forgets about adjusting the weights sequentially from the output layer to the input layer, and instead adjusts the entire set of weights at once. The second feature is that it passes the entire set of patterns through the network on one stage of iteration and uses the sum of the squares of all of the errors for all the patterns as the objective function. Another feature of the strategy is that it uses a nonlinear optimization code that accommodates constraints, such as the generalized reduced gradient method or successive quadratic programming, to adjust all the weights and other parameters.< >

关键词： backpropagation algorithms Artificial neural networks Optimization methods Gradient methods Quadratic programming Iterative algorithms Chemical engineering Control system synthesis Surfaces Transfer functions

来源：评论

学校读者我要写书评

暂无评论

Comparison of backpropagation and synthetic aperture imaging algorithms for processing GPR data

Comparison of backpropagation and synthetic aperture imaging...

引用

Antennas and Propagation Society International Symposium

作者： M.B. Kagalenko W.H. Weedon Center For Electromagnetics Research Northeastern University Boston MA USA

The synthetic aperture imaging (SAI) and backpropagation imaging (BPI) algorithms are compared for reconstructing a representation of scattering objects from time-domain ground-penetrating radar data. Synthetic data produced by a FDTD forward solver is used as a basis for the comparison. We assume initially a homogeneous, lossless host medium. The BPI algorithm, which includes waveform diffractions, is shown to result in a better focused image than SAI, with fewer artifacts. The superiority of the BPI algorithm is particularly evident at lower frequencies, where the scattering objects are on the order of the wavelength of the incident field.

关键词： backpropagation algorithms Ground penetrating radar Time domain analysis Radar scattering Electromagnetic scattering Finite difference methods Frequency Soil Transceivers Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

SENSOR VALIDATION FOR POWER-PLANTS USING ADAPTIVE backpropagation NEURAL NETWORK

引用

IEEE TRANSACTIONS ON NUCLEAR SCIENCE 1990年第2期37卷 1040-1047页

作者： ERYUREK, E UPADHYAYA, BR Department of Nuclear Engineering University of Tennessee Knoxville TN USA

Signal validation and process monitoring problems in many cases require the prediction of one or more process variables in a system. The feasibility of using neural networks to characterize one variable as a function of other related variables is studied. The backpropagation network (BPN) is used to develop models of signals from both a commercial power plant and the Experimental Breeder Reactor-II (EBR-II). Several innovations are made in the algorithm, the most significant of which is the progressive adjustment of the sigmoidal threshold function and weight updating terms.< >

关键词： Power generation Adaptive systems Neural networks Monitoring Acceleration Multi-layer neural network backpropagation algorithms Steady-state Artificial neural networks Equations

来源：评论

学校读者我要写书评

暂无评论

Training neural networks: backpropagation vs. genetic algorithms

Training neural networks: backpropagation vs. genetic algori...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： M.N.H. Siddique M.O. Tokhi Department of Automatic Control and Systems Engineering University of Sheffield Sheffield UK

ISBN: (纸本)0780370449

There are a number of problems associated with training neural networks with backpropagation algorithm. The algorithm scales exponentially with increased complexity of the problem. It is very often trapped in local minima, and is not robust to changes of network parameters such as number of hidden layer neurons and learning rate. The use of genetic algorithms is a recent trend, which is good at exploring a large and complex search space, to overcome such problems. In this paper a genetic algorithm is proposed for training feedforward neural networks and its performances is investigated. The results are analyzed and compared with those obtained by the backpropagation algorithm.

关键词： Neural networks Genetic algorithms backpropagation algorithms Robustness Algorithm design and analysis Feeds Forward contracts Transfer functions Performance analysis Systems engineering and theory

来源：评论

学校读者我要写书评

暂无评论

Comparison of backpropagation, cascade-correlation and Kokonen algorithms for cloud retrieval

Comparison of backpropagation, cascade-correlation and Kokon...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： P. Blonda G. Pasquariello J. Smid Istituto Elaborazione Segnali ed Immagini C.N.R. Bari Italy Research and Data Systems Corporation Greenbelt MD USA

The expected high volume imagery data from Nasa Mission to the Planet Earth is one of the target application areas for automated cloud retrieval, and more generally for automated image classification. We used the backpropagation (BP), the cascade-correlation (CC) and Kohonen self-organizing map (SOM) neural network architectures for cloud retrieval from satellite imagery. We have used a simple scene (a mixed scene containing only cloud and ocean). This simple scene allows us to evaluate the accuracy of the classification better than a complicated scene. Both BP and CC performed at the same accuracy level, while the SOM algorithm was slightly less accurate in performing unsupervised learning. This study shows that for simple scenes, which are abundant in global monitoring satellite imagery, a simple pixel-by-pixel or 3x3 window approaches provide high accuracy classification without using complicated contextual information.

关键词： backpropagation algorithms Clouds Layout Image retrieval Satellites Planets Earth Information retrieval Image classification Neural networks

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：