检索结果-内蒙古大学图书馆

A RECURRENT NEWTON ALGORITHM AND ITS CONVERGENCE PROPERTIES

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第3期6卷 779-783页

作者： KUAN, CM Department of Economics National Taiwan University Taipei Taiwan

In this paper a recurrent Newton algorithm for an important class of recurrent neural networks is introduced. It is noted that a suitable constraint must be imposed on recurrent variables to ensure proper convergence behavior. The simulation results show that the proposed Newton algorithm with the suggested constraint perform uniformly better than the back-propagation algorithm and the Newton algorithm without the constraint, in terms of mean-squared errors.

关键词： Convergence Signal processing algorithms backpropagation algorithms Output feedback Recurrent neural networks Target recognition Neural networks Feedforward neural networks Process control System identification

来源：评论

学校读者我要写书评

暂无评论

AN ANALYSIS OF COARSE-GRAIN PARALLEL TRAINING OF A NEURAL-NET

引用

NETWORK-COMPUTATION IN NEURAL SYSTEMS 1995年第1期6卷 73-91页

作者： COETZEE, L BOTHA, EC Department of Electrical and Electronic Engineering University of Pretoria Pretoria 0002 South Africa

In modern day pattern recognition, neural nets are used extensively. General use of a feedforward neural net consists of a training phase followed by a classification phase. Classification of an unknown test vector is very fast and only consists of the propagation of the test vector through the neural net. Training involves an optimization procedure and is very time consuming since a feasible local minimum is sought in weight space. If the training algorithm is based on error backpropagation the optimization procedure consists of the following steps: computation of the activation of the net when all the training examples are presented to it;computation of an error function based on the activation;computation of the gradients at a point in weight space;and finally, the adaptation of the weight values of the net. In this paper we present an analysis of a parallel implementation of the backpropagation algorithm using conjugate-gradient optimization for a three-layered, feedforward neural network, using networked workstations as a virtual parallel machine. The instance of the virtual machine is the PVM system, developed at Oak Ridge National Laboratory. We compare the overall performance of the parallel machine with averaged sequential runs in a typical research environment. From this, we identify the general requirements such as the size of the data set and neural net which render the parallel implementation useful, compared with the sequential execution of the same neural net training procedure.

关键词： Networks Optimization Procedure Parallel Lines OAK RIDGE NATIONAL LABORATORY Neural network ERROR FUNCTIONS learning (artificial intelligence) backpropagation algorithms sequential carry test vectors Dataset Network

来源：评论

学校读者我要写书评

暂无评论

MODELING NONLINEAR FEATURES OF V-TAIL AIRCRAFT USING MNN

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 1995年第2期31卷 841-845页

作者： RAO, KD R & T Unit for Navigational Electronics Osmania University Hyderabad India

The nonlinear stability and control modeling involves a very popular high performance general aviation aircraft that uses a ''V'' tail assembly instead of the traditional inverted ''T'' tail. The nonlinear response features of this aircraft result from a well developed Dutch roll mode and are caused by a dynamic stall phenomenon that occurs on the V tail during the maneuver. A new approach using multilayered neural network (MNN) for modeling the nonlinear features of this aircraft is suggested here. Both the conventional backpropagation(BP) and the extended Kalman filter (EKF)-based learning algorithms are used for training the neural network. Simulation results that confirm the efficacy of the method are given. Further, performance comparison of the EKF based and the conventional BP algorithms is made to highlight the effectiveness of the EKF based learning algorithm.

关键词： Tail Multi-layer neural network Neural networks backpropagation algorithms Aircraft propulsion Aircraft manufacture Stability Aerospace control Assembly Aerodynamics

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control Using Neural Networks

引用

IEEE Control Systems 1995年第5期15卷 61-66页

作者： Draeger, Andreas Engell, Sebastian Ranke, Horst Process Control Group Department of Chemical Engineering University of Dortmund D-44221 Dortmund Germany

In this article, we present the application of a neural-network-based model predictive control scheme to control pH in a laboratory-scale neutralization reactor. We use a feedforward neural network as the nonlinear prediction model in an extended DMC-algorithm to control the pH-value. The training data set for the neural network was obtained from measurements of the inputs and outputs of the real plant operating with a PI-controller. Thus, no a priori information about the dynamics of the plant and no special operating conditions of the plant were needed to design the controller. The training algorithm used is a combination of an adaptive backpropagation algorithm that tunes the connection weights with a genetic algorithm to modify the slopes of the activation function of each neuron. This combination turned out to be very robust against getting caught in local minima and it is very insensitive to the initial settings of the weights of the network. Experimental results show that the resulting control algorithm performs much better than the conventional PI-controller which was used for the generation of the training data set.< >

关键词： Predictive models Predictive control Neural networks Training data backpropagation algorithms Laboratories Inductors Feedforward neural networks Genetic algorithms Neurons

来源：评论

学校读者我要写书评

暂无评论

Genetic algorithm based pattern allocation schemes for training set parallelism in backpropagation neural networks

Genetic algorithm based pattern allocation schemes for train...

引用

IEEE International Conference on Evolutionary Computation

作者： Shou King Foo P. Saratchandran N. Sundararajan School of Electrical & Electronic Engineering Nanyang Technological University Singapore

Training set parallelization is an efficient method to optimize the training procedure performance of the backpropagation neural network algorithm. In training set parallelism, the training patterns are distributed 'optimally' among a heterogeneous array of processors, optimality criterion obtain the minimum training time per epoch. Earlier studies on heterogeneous transputers connected in a pipeline-ring topology have indicated that the above optimization problem results in a mixed integer programming problem and results in large computation time to find the optimal pattern allocations. In this paper, a genetic algorithm is used as an optimization tool to find the optimal allocation of patterns. The approach is illustrated using two benchmark problems, the 256-8-256 Encoder and NETTALK problems. Results indicate that when 'a priori' information is not used, the computation time needed by the genetic algorithm is comparable to that obtained by mixed integer programming. However, when 'a priori' information is used, the genetic algorithm results in significant reduction in computation time for finding the optimal solution.

关键词： Genetic algorithms Parallel processing backpropagation algorithms Linear programming Neural networks Intelligent networks Optimization methods Network topology Multi-layer neural network Analytical models

来源：评论

学校读者我要写书评

暂无评论

Neural training of complex sequential associations using recurrent continuous backpropagation

Neural training of complex sequential associations using rec...

引用

International Conference on Neural Networks

作者： L.H. Chen P.B. Tan M.K. Weir S.K. Foo School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore

Proposes a path-based neural network algorithm called recurrent continuous backpropagation two (RCBP-2) for complex sequential processing using a gradient descent method. Under the path-based approach, the goal weights are a collection of weight states. Coupled with the underlying continuity of training exemplars and sequential nature of the system attributes, RCBP-2 can achieve arbitrarily close approximations of complex trajectories within a fixed and relatively small network topology. The performance of RCBP-2 is also monitored by training and subsequently testing on a 4-orbits problem. The results show that RCBP-2 results in a fast and efficient algorithm for complex sequential processing.

关键词： Neural networks Recurrent neural networks backpropagation algorithms Network topology Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

Mapping of backpropagation learning onto distributed memory multiprocessors

Mapping of backpropagation learning onto distributed memory ...

引用

IEEE International Conference on algorithms and Architectures for Parallel Processing (ICAP)

作者： S. Mahapatra R.N. Mahapatra Department of Electronics & Electrical Communication Engineering Indian Institute of Technology Kharagpur India Department of Computer Science Engineering & Applications Regional Engineering College Orissa India

This paper presents a mapping scheme for parallel pipelined execution of the backpropagation Learning Algorithm on distributed memory multiprocessors (DMMs). The proposed implementation exhibits training set parallelism that involves batch updating. Simple algorithms have been presented, which allow the data transfer involved in both forward and backward executions phases of the backpropagation algorithm to be carried out with a small communication overhead. The effectiveness of our mapping has been illustrated, by estimating the speedup of a proposed implementation on an array of T-805 transputers.< >

关键词： Multi-layer neural network Parallel processing backpropagation algorithms Neural networks Neurons Performance analysis Parallel architectures Visualization Computer science Application software

来源：评论

学校读者我要写书评

暂无评论

Self-adaptive learning rates in backpropagation algorithm improve its function approximation performance

Self-adaptive learning rates in backpropagation algorithm im...

引用

International Conference on Neural Networks

作者： U. Bhattacharya S.K. Parui Computer Vision and Pattern Recognition Unit Indian Statistical Institute Calcutta India

The backpropagation algorithm helps a multilayer perceptron to learn to map a set of inputs to a set of outputs. But often its function approximation performance is not impressive. In this paper the authors demonstrate that self-adaptation of the learning rate of the backpropagation algorithm helps in improving the approximation of a function. The modified backpropagation algorithm with self-adaptive learning rates is based on a combination of two updating rules-one for updating the connection weights and the other for updating the learning rate. The method for learning rate updating implements the gradient descent principle on the error surface. Simulation results with astrophysical data are presented.

关键词： backpropagation algorithms Function approximation Multilayer perceptrons Approximation algorithms Computer vision Pattern recognition Neural networks Joining processes Computer errors Computational modeling

来源：评论

学校读者我要写书评

暂无评论

A parallel mapping of backpropagation algorithm for mesh signal processor

A parallel mapping of backpropagation algorithm for mesh sig...

引用

IEEE Workshop on Neural Networks for Signal Processing

作者： S.A. Khan V.K. Madisetti Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA

Presents a technique for mapping the backpropagation learning algorithm on a mesh signal processor. The optimal sub-partitioning of computation and communication, and data replication techniques are the key features of the authors' algorithm. Theoretical analysis and simulation results, using the MIT Lincoln Lab simulator, show that the authors' scheme performs better than the other schemes.

关键词： Signal mapping backpropagation algorithms Signal processing Signal processing algorithms Digital signal processing Concurrent computing Data structures Broadcasting Algorithm design and analysis Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Self partitioning backpropagation network for target recognition

Self partitioning backpropagation network for target recogni...

引用

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

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：