神经网络

The fault current limiter with thyristor controlled series compensation is analysed. The control model with ANN composed of two independent subnets is presented.

对具有可控串补功能的短路限流器进行了分析，提出了由两个独立子网络组成的人工神经网络控制模型。

This method uses its own learning mechanism to create the domain of the decision. It can make best use of the samples by training each sample individually and obtaining the balanced weights with good convergence.

针对神经网络在结构损伤检测应用中的不足，本文对BP(back-propagation)算法提出了改进——权值阈值同步学习的BP 算法，并着重分析了改进BP 网络建模中的一些不确定的因素，提出了建模中的注意要点和选择建议。

According to compare the results with decision tree, support vector machine, and RBF neural network, the neural network classifier with dynamic threshold has better forecasting accuracy, stability and generalization ability.

通过与决策树、支持向量机、RBF网络等方法的比较结果表明，基于动态闽值的神经网络分类器具有更好的预测精度、稳定性以及泛化能力。

Based on neural network identification procedures, procedures adopted a three-tier network training BP, with its defi...

基于神经网络的识别程序，程序采用三层BP网络训练，采用了普通定义中加入动量因子的训练法，精确度很高。

Every research result shows that Bayesian Classifier acts as one important class technology, Compared with Decision Tree Construction and Neural Network Classifier, Bayesian Classifier can adequately bring into play its incertitude discursion ability, so it can ameliorate learning ability and increase accuracy of forecast, it have better class effect in some conditions.

各种研究结果表明：贝叶斯分类作为数据挖掘中一项重要的分类技术，与决策树和神经网络分类器相比，贝叶斯网络分类器可以充分发挥它的不确定性推理能力，从而改善学习效果，提高预测准确率，在某些情况下具有更好的分类效果。

The scale 7, 10 and 13 are used to extract the feature vectors, which are used to train the artificial neural network. The trained neural network is used to classify semen cuscutaes and Japanese dodder seeds, which are collected from different places all over the country.

选择第7、10、13分解层数的特征向量，进行人工神经网络训练，再用训练出来的网络对不同产地的植物种子菟丝子和金灯藤所得FTIR小波提取的特征向量进行分类。

A new and efficient learning algorithm of asociative memory neural network is proposed, with the following characteristics:(1)it can store any given training pattern set no matter how much and what correlation among them may be;(2)the smallest domain of attraction of training patterns is maximized;(3)each domain of attraction of training patterns is guaranteed to be as large as possible;(4)the designed associative memory network is globally stable.

摘要提出一种新的联想记忆网络模型的有效学习算法，它具有下述特点：(1)可以全部存储任意给定的训练模式集，即对于训练模式的数目和它们之间相关性的强弱没有限制；(2)最小的训练模型吸引域达到最大；(3)在(2)的基础上，每个训练模式具有尽可能大的吸引域；(4)联想记忆神经网络是全局稳定的。

In this paper, we focuse on the dynamic enterprise resource-share and resource scheduling based on net.

在进行系统集成开发的基础上，本论文主要研究基于网络的企业动态资源共享和资源调度问题，主要工作如下：对Hopfield神经网络和模拟退火算法进行了研究。

Neural network method for solving generalized eigenvalue and eigenvector problems is discussed, including problems about the network model and its convergence.

讨论了广义特征根问题求解的神经网络方法，包括网络模型，稳定性问题等。

According to optical theory of distortion and utilizing BP neural network to approach nonlinear distortion, distortion correction mathematic model of whole field was set up through training the distortion measurement data which were measured by distortion detection device. This device has eleven equidistance points of laser goals and is designed based on the basis of distortion mechanism and radical character.

根据畸变光学原理，利用BP神经网络对非线性畸变进行良好的逼近，通过对由畸变测量装置获得的数据进行训练建立网络模型，从而建立整个视场畸变校正的数学模型。

We have no common name for a mime of Sophron or Xenarchus and a Socratic Conversation; and we should still be without one even if the imitation in the two instances were in trimeters or elegiacs or some other kind of verse--though it is the way with people to tack on 'poet' to the name of a metre, and talk of elegiac-poets and epic-poets, thinking that they call them poets not by reason of the imitative nature of their work, but indiscriminately by reason of the metre they write in.

索夫农 、森那库斯和苏格拉底式的对话采用的模仿没有一个公共的名称；三音步诗、挽歌体或其他类型的诗的模仿也没有——人们把&诗人&这一名词和格律名称结合到一起，称之为挽歌体诗人或者史诗诗人，他们被称为诗人，似乎只是因为遵守格律写作，而非他们作品的模仿本质。

The relationship between communicative competence and grammar teaching should be that of the ends and the means.

交际能力和语法的关系应该是目标与途径的关系。