检索结果-内蒙古大学图书馆

Efficient mapping of backpropagation algorithm onto a network of workstations

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 1998年第6期28卷 841-848页

作者： Sudhakar, V Murthy, CSR Indian Inst Technol Dept Comp Sci & Engn Madras 600036 Tamil Nadu India

In this paper, we present an efficient technique for mapping a backpropagation (BP) learning algorithm for multilayered neural networks onto a network of workstations (NOW's). We adopt a vertical partitioning scheme, where each layer in the neural network is divided into p disjoint partitions, and map each partition onto an independent workstation in a network of p workstations. We present a fully distributed version of the BP algorithm and also its speedup analysis. We compare the performance of our algorithm with a recent work involving the vertical partitioning approach for mapping the BP algorithm onto a distributed memory multiprocessor. Our results on SUN 3/50 NOW's show that we are able to achieve better speedups by using only two communication sets and also by avoiding some redundancy in the weights computation for one training cycle of the algorithm.

关键词： backpropagation algorithm distributed memory multiprocessors multilayered neural networks network of workstations network partitioning pattern partitioning performance analysis

来源：评论

学校读者我要写书评

暂无评论

Efficient training and improved performance of multilayer perceptron in pattern classification

引用

NEUROCOMPUTING 2000年第1-4期34卷 11-27页

作者： Chaudhuri, BB Bhattacharya, U Indian Stat Inst Comp Vis & Pattern Recognit Unit Calcutta 700035 W Bengal India

In pattern recognition problems, the convergence of backpropagation training algorithm of a multilayer perceptron is slow if the concerned classes have complex decision boundary. To improve the performance, we propose a technique, which at first cleverly picks up samples near the decision boundary without actually knowing the position of decision boundary. To choose the training samples, a larger set of data with known class label is considered. For each datum, its k-neighbours are found. If the datum is near the decision boundary, then all of these k-neighbours would not come from the same class. A training set, generated using this idea, results in quick and better convergence of the training algorithm. To get more symmetric neighbours, the nearest centroid neighbourhood (Chaudhuri, Pattern Recognition Lett. 17 (1996) 11-17) is used. The performance of the technique has been tested on synthetic data as well as speech vowel data in two Indian languages. (C) 2000 Elsevier Science B.V. All rights reserved.

关键词： backpropagation algorithm multilayer perceptron faster training pattern classification

来源：评论

学校读者我要写书评

暂无评论

A novel fuzzy neural network based distance relaying scheme

引用

IEEE TRANSACTIONS ON POWER DELIVERY 2000年第3期15卷 902-907页

作者： Dash, PK Pradhan, AK Panda, G Reg Engn Coll Dept Elect Engn Rourkela India

This paper presents a nem approach to distance relaying using fuzzy neural network (FNN). The FNN can be viewed either as a fuzzy system, a neural network or fuzzy neural network. The structure is seen as a neural network for training and a fuzzy viewpoint is utilized to gain insight into the system and to simplify the model. The number of rules is determined by the data itself and therefore smaller number of rules is produced. The network is trained with back propagation algorithm. A pruning strategy is applied to eliminate the redundant rules and fuzzification neurons. consequently a compact structure is achieved. The classification and location tasks are accomplished by using different FNN's, Once the fault type is identified by the FNN classifier the selected fault locating FNN estimates the location of the fault accurately, Normalized peaks of fundamental voltage and current waveforms are considered as inputs to all the networks and an additional input derived from df component is fed to fault locating networks. The peaks and de component are extracted from sampled signals by the EKF, Test results show that the nem approach provides robust and accurate classification/location of faults for a variety of power system operating conditions even with resistance in the fault path.

关键词： backpropagation fault location fuzzy neural nets power system analysis computing power system faults power system protection relay protection DC component EKF backpropagation algorithm current waveform distance relaying scheme fault path resistance fault Fault location Power system analysis computing Power system faults backpropagation algorithms back propagation Fuzzy neural networks Relay protection Power system protection DC component

来源：评论

学校读者我要写书评

暂无评论

Use of an artificial neural network to predict population dynamics of the forest-pest pine needle gall midge (Diptera: Cecidomyiida)

引用

ENVIRONMENTAL ENTOMOLOGY 2000年第6期29卷 1208-1215页

作者： Chon, TS Park, YS Kim, JM Lee, BY Chung, YJ Kim, Y Pusan Natl Univ Dept Biol Pusan 609735 South Korea

The backpropagation algorithm in artificial neural networks was used to forecast dynamic data of a forest pest population of the pine needle gall midge, Thecodiplosis japonensis Uchida et Inouye, a serious pest in pine trees in northeast Asia. Data for changes in population density were sequentially given as input, whereas densities of subsequent samplings were provided as matching target data for training of the network. Convergence was reached, generally after 20,000 iterations with learning coefficients of 0.5-0.8. When new input data were given to the trained network, recognition was possible and population density at the subsequent sampling time could be predicted.

关键词： Thecodiplosis japonensis pine needle gall midge population dynamics prediction artificial neural network backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Force learn algorithm - training a neural net with patterns which have highest errors 5

Force learn algorithm - training a neural net with patterns ...

引用

5th Seminar on Neural Network Applications in Electrical Engineering

作者： Ilic, V Univ Belgrade Fac Elect Engn YU-11001 Belgrade Yugoslavia

This study describes training methods of the neural nets with the backpropagation algorithm of learning in which the priority is given to the patterns of the training sd with the maximum error during the training.

ISBN: (纸本)0780355121

关键词： neural networks backpropagation algorithm training set

来源：评论

学校读者我要写书评

暂无评论

On a weight limit approach for enhancing fault tolerance of feedforward neural networks

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2000年第11期E83D卷 1931-1939页

作者： Kamiura, N Isokawa, T Hata, Y Matsui, N Yamato, K Himeji Inst Technol Dept Comp Engn Himeji Hyogo 6712201 Japan Hyogo Med Univ Dept Econ & Informat Sci Kakogawa 6750101 Japan

To enhance fault tolerance ability of the feedforward neural networks (NNs for short) implemented in hardware, we discuss the learning algorithm that converges without adding extra neurons and a large amount of extra learning time and cycles. Our algorithm modified from the standard backpropagation algorithm (SBPA for short) limits synaptic weights of neurons in range during learning phase. The upper and lower bounds of the weights are calculated according to the average and standard deviation of them. Then our algorithm reupdates any weight beyond the calculated range to the upper or lower bound. Since the above enables us to decrease the standard deviation of the weights, it is useful in enhancing fault tolerance. We apply NNs trained with other algorithms and our one to a character recognition problem. It is shown that our one is superior to other ones in reliability, extra learning time and/or extra learning cycles. Besides we clarify that our algorithm never degrades the generalization ability of NNs although it coerces the weights within the calculated range.

关键词： feedforward neural networks fault tolerance backpropagation algorithm stuck-at faults generalization ability

来源：评论

学校读者我要写书评

暂无评论

Neural Network Speed Identification Scheme for Speed Sensor-less DTC Induction Motor Drive System

Neural Network Speed Identification Scheme for Speed Sensor-...

引用

The Third International Power Electronics and Motion Control Conference

作者： Xianmin Ma Zhi Na Department of Automation Engineering Of XiE28099an University of Science and Technology Xi'an Shanxi China Department of Automation Engineering Xi''an University of Science and Technology Xi'an Shanxi China

ISBN: (纸本)780003464X

A novel neural network speed identification scheme for the speed sensorless direct torque control (DTC) of an induction motor drive system is presented in the paper. The system uses current and voltage sensors for rotor speed and rotor flux estimation with a digital signal processor (DSP) TMS320F240 in a closed loop control system. Rotor speed identification is based on the model reference adaptive control (MRAC) theory with a neural network using the backpropagation (BP) algorithm. The suggested speed identification method has been validated by a simulation study.

关键词： induction motor drives machine vector control control system synthesis neurocontrollers velocity control torque control machine theory parameter estimation model reference adaptive control systems control system analysis backpropagation neural network speed identification scheme speed sensorless direct torque control induction motor drive control design current sensors voltage sensors rotor speed estimation rotor flux estimation closed loop control system control simulation model reference adaptive control backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of neural networks to the modelling of some constitutive laws

引用

NEURAL NETWORKS 1999年第2期12卷 371-392页

作者： Pernot, S Lamarque, CH Ecole Natl Travaux Publ Etat DGCB LGM URA CNRS 1652 F-69518 Vaulx En Velin France

This study investigates the modelling of constitutive laws of materials by neural networks. Material behaviour is no longer represented mathematically but is described by neuronal modelling. The main aim is to build a neural network directly from experimental results (the learning phase). We give several examples of constitutive laws (Hooke, Sargin, etc.) using a backpropagation algorithm. Then we show that abilities of adjustment, memorisation and anticipation of neural networks permit us to develop a method of classification of constitutive laws. (C) 1999 Elsevier Science Ltd. All rights reserved.

关键词： constitutive laws materials neural networks perceptron modelling backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Compact building blocks for artificial neural networks

引用

ELECTRONICS LETTERS 1999年第1期35卷 56-57页

作者： Meléndez-Rodríguez, M Silva-Martínez, J Natl Inst Astrophys Opt & Elect Integrated Circuit Design Grp Puebla 72000 Mexico

A four quadrant analogue multiplier, an activation function and a differentiator intended for the implementation of backpropagation algorithms are proposed. The priorities for the design are low-power, low-voltage, an... 详细信息

关键词： differentiating circuits neural nets artificial neural network Neural net devices Neural nets (circuit implementations) analogue multipliers silicon area activation function analogue multiplier backpropagation differentiator backpropagation algorithm low-power electronics low-power low-voltage circuit building block

来源：评论

学校读者我要写书评

暂无评论

Accelerating neural network training using weight extrapolations

引用

NEURAL NETWORKS 1999年第9期12卷 1285-1299页

作者： Kamarthi, SV Pittner, S Northeastern Univ Dept Mech Ind & Mfg Engn Snell Eng Ctr 334 Boston MA 02115 USA

The backpropagation (BP) algorithm for training feedforward neural networks has proven robust even for difficult problems. However, its high performance results are attained at the expense of a long training time to adjust the network parameters, which can be discouraging in many real-world applications. Even on relatively simple problems, standard BP often requires a lengthy training process in which the complete set of training examples is processed hundreds or thousands of times. In this paper, a universal acceleration technique for the BP algorithm based on extrapolation of each individual interconnection weight is presented. This extrapolation procedure is easy to implement and is activated only a few times in between iterations of the conventional BP algorithm. This procedure, unlike earlier acceleration procedures, minimally alters the computational structure of the BP algorithm. The viability of this new approach is demonstrated on three examples. The results suggest that it leads to significant savings in computation time of the standard BP algorithm. Moreover, the solution computed by the proposed approach is always located in close proximity to the one obtained by the conventional BP procedure. Hence, the proposed method provides a real acceleration of the BP algorithm without degrading the usefulness of its solutions. The performance of the new method is also compared with that of the conjugate gradient algorithm, which is an improved and faster version of the BP algorithm. (C) 1999 Elsevier Science Ltd. All rights reserved.

关键词： multilayer neural networks backpropagation algorithm convergence acceleration extrapolation methods parameter estimation linear regression conjugate gradient method relative entropy

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：