检索结果-内蒙古大学图书馆

IEEE Southeastcon

作者： H.S. Ranganath D. Kerstetter Computer Science Departmentt University of Alabama Huntsville Huntsville AL USA

A method for qualifying the degree of noncooperation that exists among the target members of the training set is presented. Both the network architecture and the training algorithm are taken into consideration while computing non-cooperation measures. Based on these measures, the network automatically creates several topologically identical partitions. Each partition learns a subset of the targets. The partitioning takes place only when necessary and requires minima computation. Each partition is simple with only one hidden layer and one node in the output layer. A fusion network combines partial results to produce the final response. Simulation results indicate that the method is robust and capable of self organization to overcome the ill effects of non-cooperating targets in the training set. Thus the network complexity and training time are significantly reduced. The self partitioning neural network (SPNN) approach has been tested through extensive simulation using more than 15 sets of real ATR data provided by the US Army Missile Command. Each data set consisted of hundreds of images which were extracted by the target detection system from the sensor's field of view for further processing. The study has indicated that the SPNN approach has the potential for use in real-time target recognition applications.

关键词： Target recognition Computer architecture Partitioning algorithms backpropagation algorithms Computer networks Computational modeling Robustness Neural networks Automatic testing Missiles

来源：评论

学校读者我要写书评

暂无评论

A modified backpropagation algorithm for neural classifiers

A modified backpropagation algorithm for neural classifiers

引用

Midwest Symposium on Circuits and Systems (MWSCAS)

作者： M.C. Bossan J.M. Seixas L.P. Caloba R.S. Penha J. Nadal COPPE/EE UFRJ Rio de Janeiro Brazil Universidade Federal do Rio de Janeiro Rio de Janeiro RJ BR COPPE Univ. Federal do Rio de Janeiro Brazil

A variation of the traditional backpropagation algorithm is presented as an alternative approach for training feedforward neural network based classifiers. This method aims to reduce the tendency of these classifiers to spend most of their time trying to achieve unnecessarily low mean square errors in very populated regions of the pattern space, while almost ignoring patterns in sparse regions of it until a large number of training steps occurs. An application of the new algorithm in particle discriminators for high energy physics experiments is shown.

关键词： backpropagation algorithms Neural networks Feedforward neural networks Pattern classification Mean square error methods Convergence Cost function Electronic mail Clustering algorithms Filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

Efficient estimation of dynamically optimal learning rate and momentum for backpropagation learning

Efficient estimation of dynamically optimal learning rate an...

引用

International Conference on Neural Networks

作者： Xiao-Hu Yu Guo-An Chen National Communications Research Laboratory Department of Radio Engineering South-East University Nanjing China

ISBN: (纸本)0780327683

This paper considers efficient estimation of dynamically optimal learning rate (LR) and momentum factor (MF) for backpropagation learning by a multilayer feedforward neural net. A novel approach exploiting the derivatives w.r.t. the LR and MF is presented, which does not need to explicitly compute the first two order derivatives in weight space, but rather makes use of the information gathered from the forward and backward procedures. Since the computational and storage burden for estimating the optimal LR and MF at most triple that of the standard backpropagation algorithm (BPA), the backpropagation learning procedure can be therefore accelerated with remarkable savings in running time. Computer simulations provided in this paper indicate that at least a magnitude of savings in running time can be achieved using the present approach.

关键词： Multi-layer neural network Neural networks Feedforward neural networks backpropagation algorithms Acceleration Computer simulation

来源：评论

学校读者我要写书评

暂无评论

Classification of human cognitive processes by the use of an improved neural backpropagation network

Classification of human cognitive processes by the use of an...

引用

International Conference on Neural Networks

作者： D. Steuer B. Schack G. Grieszbach W. Krause Department of Biomedical Engineering and Informatics Technical University Ilmenau Ilmenau Germany Department for Medical Statistics Computer Sciences and Documentation University of jean Jena Germany Institute for Psychology University of Jena Jena Germany

The analysis of human cognitive processes constitutes a great challenge for scientists of all research fields. Better methods in signal processing (that means higher resolution in time and frequency) lead to an even better explanation of the human thinking. An unsolved problem in psychology is the question of whether a change between pictorial and conceptual thinking could be the source of intellectual creativity. We attempt to show results for the classification of such elementary cognitive processes by the use of a neural backpropagation network. In one result, we introduce an advanced backpropagation algorithm, which accelerates the learning speed and stabilizes the learned net through adaptive recursive estimation methods.

关键词： Humans Psychology Coherence Testing Signal processing Signal analysis Biomedical signal processing Signal resolution backpropagation algorithms Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Hybrid nets with variable parameters: a novel approach to fast learning under backpropagation

Hybrid nets with variable parameters: a novel approach to fa...

引用

International Symposium on Intelligence in Neural and Biological Systems, INBS

作者： Jun Han C. Moraga Research Group Computational Intelligence Department of Computer Science I University of Dortmund Dortmund Germany

This paper presents a novel approach under regular backpropagation. We introduce hybrid neural nets that have different activation functions for different layers in fully connected feed forward neural nets. We change the parameters of activation functions in hidden layers and output layer to accelerate the learning speed and to reduce the oscillation respectively. Results on the two-spirals benchmark are presented which are better than any results under backpropagation feed forward nets using monotone activation functions published previously.< >

关键词： Neural networks Feeds Feedforward neural networks Attenuation backpropagation algorithms Equations Computational intelligence Computer science Acceleration Spirals

来源：评论

学校读者我要写书评

暂无评论

Statistical analysis of the single-layer backpropagation algorithm for noisy training data

Statistical analysis of the single-layer backpropagation alg...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

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

The statistical learning behavior of the single-layer backpropagation algorithm was analyzed using a system identification formulation for noise-free training data [Bershad et al. 1993]. Transient and steady-state results were obtained for the mean weight behavior, mean-square error (MSE), and probability of correct classification. The present paper extends these results to the case of noisy training data. Three new analytical results are obtained: 1) the mean weights converge to finite values even when the bias terms are zero, 2) the MSE is bounded away from zero, and 3) the probability of correct classification does not converge to unity. However, over a wide range of signal-to-noise ratios (SNRs), the noisy training data does not have a significant effect on the perceptron stationary points relative to the weight fluctuations. Hence, one concludes that noisy training data has a relatively small effect on the ability of the perceptron to learn the model weight vector F.

关键词： Statistical analysis backpropagation algorithms Training data Signal to noise ratio Statistical learning Algorithm design and analysis System identification Steady-state Probability Data analysis

来源：评论

学校读者我要写书评

暂无评论

A unifying view of stochastic approximation, Kalman filter and backpropagation

A unifying view of stochastic approximation, Kalman filter a...

引用

IEEE Workshop on Neural Networks for Signal Processing

作者： E. Capobianco Statistics Department University of Padua Italy

In this paper the relationships between the stochastic approximation, the Kalman filter and the backpropagation algorithms are investigated. We show that when the neural network architecture at hand can be formalized such that the approximation of the optimum for a nonlinear objective function is the problem for which we seek a solution, then both stochastic approximation techniques and appropriate Kalman filters can be employed in order to reach the goal but the latter can also handle various structural characteristics of the stochastic processes involved and suggest a more efficient two-step estimator.

关键词： Stochastic processes backpropagation algorithms Neural networks Least squares approximation Approximation algorithms Least squares methods Parameter estimation Newton method Recursive estimation Statistics

来源：评论

学校读者我要写书评

暂无评论

An analysis of network parallelism of backpropagation neural networks on a transputer array

An analysis of network parallelism of backpropagation neural...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： R. Arularasan P. Saratchandran N. Sundararajan School of Electrical and Electronic Engineering Nanyang Technological University Singapore

This paper presents the development of a theoretical model for parallel implementation of backpropagation (BP) neural networks using the "network parallelism" paradigm. The case where the number of nodes in each layer is equally distributed among the processors is considered. The model is developed for a homogeneous array of message passing processors with only local memory. The developed model predicts the training time for a given neural network without having to set up the hardware and run the experiments. The accuracy of the model is verified by comparing the predicted training time using the theoretical model with the actual experimental values for the case of an array of T805 transputers connected in a ring topology for benchmark neural network problems like the Encoder and Nettalk.

关键词： Neural networks Message passing Artificial neural networks Network topology Predictive models Convergence Neural network hardware backpropagation algorithms Computer networks Concurrent computing

来源：评论

学校读者我要写书评

暂无评论

Modified backpropagation algorithms for training the multilayer feedforward neural networks with hard-limiting neurons

Modified backpropagation algorithms for training the multila...

引用

Canadian Conference on Electrical and Computer Engineering (CCECE)

作者： Xiangui Yu N.K. Loh G.A. Jullien W.C. Miller Department of Electrical Engineering University of Windsor Windsor ONT Canada Center for Robotics and Advanced Automation Dodge Hall of Engineering Oakland University Rochester MI USA

This paper introduces modified backpropagation algorithms for training multilayer feedforward neural networks with hard-limiting neurons. Transforming neuron activation functions are used in all the hidden layers, which are the modified continuous sigmoidal functions with an adaptive steepness factors. In the training process, this steepness factor varies from a small positive value to infinite with the decrease of the sum square error. Thus, a multilayer feedforward neural network can be trained with the resultant architecture only composed of hard limiting neurons. The learning algorithm is similar to the conventional backpropagation algorithm. Only the derivatives of the hidden neural activation functions are modified. Extensive numerical simulations are presented to show the feasibility of the proposed algorithm. In addition, the numerical properties of the proposed algorithm are discussed and comparisons of the proposed algorithm with other algorithms are made.< >

关键词： Multi-layer neural network backpropagation algorithms Neural networks Feedforward neural networks Neurons Multilayer perceptrons Very large scale integration Robotics and automation Electronic mail Numerical simulation

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Fuzzy Controllers

引用

IFAC Proceedings Volumes 1995年第19期28卷 1-9页

作者： Petr Horáček Zdenek Binder Czech Technical University of Prague Faculty of Electrical Engineering Dept. of Control Engineering Karlovo nam. 13 CZ-121 35 Prague 2 Czech Republic Institut National Polytechnique de Grenoble ENSIEG Laboratoire d’ Automatique de Grenoble B.P.46 38402 Saint-Martin-d’Hères France

The paper presents Fuzzy Logic Controllers (FLC) with hierarchically structured rule base as nonlinear blocks used in a control system for direct control or supervision of standard controllers. Unified approach based on Fuzzy Logic Neural Networks (FLNN) is used to reveal the essential functions of a FLC. The FLNN is then extended to the case where decomposition of a rule base leads to simplification of controller design and tuning. Two structures of hierarchically organized groups of rules are discussed. Singlestage decision making structure with groups of rules organized hierarchically according to their specificity and a multi-stage decision making architecture with chained rules. Data induced error backpropagation technique for fine tuning of parameters of the second structure is derived.

关键词： Fuzzy control Fuzzy inputs Neural networks Hierarchical control backpropagation algorithms

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：