神经网络

In the family of neural network model, this kind of model is first to be put into use for solving combinatorial optimization problem.

在人工神经网络众多的模型中，这一网络模型是用于求解组合优化问题最早，也是最常用的一种。

Bp network algorithm to achieve a single network, learning neural network with common people.

这是bp网络算法的一个单网实现，对于学习神经网络的人来说常用用。

It is proved that this algorithm can be used to build a B|spline neural network with minimum hidden units to approximate any continuous function defined on compact set to a prescribed accuracy.

对于3层神经网络而言，输入至输出的映射实际上是通过基函数的加权组合来实现的，当基函数取不同时，网络有不同的性质

In order to solve the problems that generic ANN is lack of incremental learning and easily to make a wrong or a leak diagnosis, the paper has put forward a composite radial basis function network classifier oriented the diagnosis task, and studied the realization algorithm of this classifier in detail.

针对一般的神经网络不具备渐进学习功能、在故障诊断时易发生漏诊或误诊的问题，提出了一种面向诊断任务的组合径向基函数网络分类器，详细研究了该分类器的实现算法。

The back propagation artificial neural net is applied in random response analysis of structure. Thus, the process of finite element computing repeat several times and train BP net between the random input variables and the corresponding response parameters.

采用BP人工神经网络这一映射迅速的运算方法，通过计算少量样本对应的有限元结果，进行训练，将训练好的网络用于结构的随机响应分析。

Since the constringency of the BP neural network algorithm is too slow and generalization capability of neural network is not ideal, the disadvantageseffect the classification identification.

BP神经网络算法存在收敛速度慢和网络泛化能力差的缺点，影响分类识别率。

A new objective function of constructional learning is presented.

神经网络的结构学习就是要确定网络的拓扑，使之有较好的泛化能力。

And further more it gives a proof that this optimization problem can be seen as a convex programming in exponential neural manifold.

即将神经网络看作为统计模型，使用常用的统计推断技术，通过优化学习代价函数，对网络参数进行调整，从而达到学习的目的。

Some widely used artificial neural networks such as BP, RBF and ARTMAP were discussed on the common points they shared when solving nonlinear regression problems. A framework, proposed accordingly, suggested that such problems should be implemented in two steps: sample covering and modelbased map regression.

分析了BP、RBF和ARTMAP等人工神经网络在实现非线性映射方面的共同之处，基于RBF等网络对于人脑功能方面的模拟和仿生模式识别的思想，总结出一种处理这类问题的基本框架。

From the perspective of covering points in high-dimensional space, we discussed the theory of constrictive PONN based on knowledge rules. PONN's general constructive algorithm and its two special methods based on random sampling and barycenter rules respectively were proposed in this paper.

从高维空间样本点覆盖的角度，讨论了基于知识规则的构造性优先排序神经网络算法的原理，提出了网络构造过程的一般算法以及基于随机取样规则和重心点规则的两个实例算法。

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。