神经网络

The simulation results show that the novel BP wavelet neural network based on IPSO not only has the good local property of wavelet analysis and the learning and classification capability of artificial neural network, but also has the fast global searching advantage of particle swarm optimization algorithm.

实验结果表明，基于改进的粒子群优化算法的BP小波网络不仅具有小波分析良好的局部特性以及神经网络的学习、分类能力，而且具有粒子群优化算法全局快速寻优的特点。

We have proposed an easy way to transfer the isomerous data to isomorphic data, to unitary eigenvector to adapt to the requirement of the artificial neural networks.

本文主要研究人工神经网络应用于入侵检测在实际检测中的表现以及对未知网络攻击的检测效果。

Using RBF neural network substitutes BP network as the approximation of implicit performance function, and the response surface is formed in the sphere of hyper-pyramid at iteration step.

采用径向基函数神经网络，代替目前常用的BP网络，迭代过程中在超锥体的范围内构造响应面，逼近隐式的非线性功能函数。

And the formula of Jacobin matrix for unknown systems is given, which is used to train the neural networks controller in closed systems.

总结了非线性系统的神经网络的辨识方法和控制方法，提出了针对未知非线性系统的BP网络自适应辨识结构。

The magnitude of opened angle at a point p i in the contour can be easily calculated by the law of cosines, and its local extreme correspond to the sharper changes of the contour of the mode.

同时将特征匹配定义为模型特征与遮挡图象特征之间的对应，若这种对应被映射到 Hopfield神经网络上，则该网络即可用于完成全局特征匹配。

There are five important soft sensor models of moisture have been established in this paper: the moisture model of The Recursive Least Square based on Lethe gene, the moisture model of Principal Component Regression , the moisture model of Partial Least Square, the moisture model of BP Nerve Network, the moisture model based on PLS—BP. All of these soft sensor models of moisture are systematically analysed by using Compound Correlative Coefficient. The factors which influence control of moisture are discussed on detail in this paper.

建立了五个重要的水分软测量模型，即渐消记忆递推最小二乘法水分模型；主成分分析法水分模型；偏最小二乘法水分模型；BP 神经网络水分模型；偏最小二乘BP 网络水分模型；对以上水分软测量模型用统一的评价指标复相关系数对它们的优劣进行了详细的分析，选出最适合水分建模的建模方法，同时对影响水分的各个因素进行了深入的分析和探讨。

Genetic-based fuzzy neural network is used to fuse a lot of data of information handling unit, and the method of using Genetic Algorithm to optimize general network parameter and using BP Algorithm to modulate and optimize local parameter is presented.

采用基于遗传算法的模糊神经网络对信息处理单元的大量数据进行数据融合，提出了采用遗传算法优化具有全局性的网络参数，用BP算法调节和优化具有局部性的参数。

On the basis of the researching the neural network theory, presenting the neural network model (N-SearCut model) for searching for minimal cutset of a graph, proving the stability of this model, analyzing the dynamic behavior of this model, deducing a series of corresponding theorems and affording an academic fundaments for solving optimization problem based on this model.

在研究人工神经元网络理论基础之上，提出了搜索图最小割集的神经网络模型——N-SearCut模型，证明了该模型的稳定性，分析了该模型的动态特性，导出了一系列的定理，为运用该模型进行优化问题的求解提供了理论依据。

Setting forth the realization method by hardware for searching minimal cutset of a graph with N-SearCut model. Then this method affords theory and practice fundament for solving this puzzle of searching for minimal cutset in reliability evaluation of power system.

提出了运用N-SearCut神经网络模型搜索图最小割集的全硬件实现方法，为更理想地解决网络可靠性评估中出现的最小割集搜索这一瓶颈问题提出了新的思路，提供了理论和实践依据。

Then we prove a nonsmooth minimax theorem by usingsome relative results about multi-valued maximal monotone mappings. Finally, we construct a nonsmooth minimax network to search for thesaddle points of the saddle functional. We have also proved that thetrajectory of the network is asymptotically convergent to thesaddle point of the saddle functional by usying Lyapunov function.

我们先介绍有关Clarke的广义梯度，次梯度及鞍泛函的有关结论；然后利用多值极大单调映象的满射性结果证明了一个非光滑的minimax定理；最后建立了一个非光滑的minimax神经网络来求解泛函的鞍点，并在一定的条件下构造出LYAPUNOV函数来证明网络的轨道渐近收敛于鞍泛函的鞍点。

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。