网络函数

Several strong results on neural network approximation capability obtained in this dissertation are important in the approximation theory and applications of neural networks.

本文系统地研究了多层神经网络的非线性逼近能力，给出了多层网络可一致逼近有限维空间R〓紧集上的连续函数、无穷维函数空间紧集上的连续泛函和连续算子以及布尔函数的理论证明。

A control strategy using Mutual Mapping Neural Network to compute the solution of the backward and forward kinematics was presented in this paper. MMNN was consisted of two NN and one modify function, one NN was used for forward kinematics calculation, and another for Jacobi matrix calculation, the modify function was formed based on Lyapunov function.

双向映射神经元网络主要由两个神经网络和一个修正函数构成，其中一个神经网络用来进行正运动学求解，另一个神经网络用来计算雅可比矩阵，修正算法是根据李雅普诺夫函数来计算的。

By means of the projection method,adding a small disturbing function to the objective function, the penalty method, andthe gradient method, this dissertation proposes several neural networks for solvingsaddle point problems and minimum radius of ball-coverings problems, and investi-gates the stability of the proposed networks by the LaSalle invariance principle andthe Lyapunov method, so as to design neural networks which avoid getting stuck inthe local minimum.

本文针对约束鞍点问题和球覆盖最小半径的计算问题，分别利用投影法、对目标函数加上很小"扰动函数"的逼近法、罚函数法和梯度法等建立神经网络模型进行求解，并基于LaSalle不变集原理和Lyapunov直接法等工具，对模型的动态特性进行研究，从而设计出避免陷入局部极小的优化计算神经网络模型。

In this paper chip shapes were recognized by using of radbas neural network. We put forward area ratio feature, Euler number feature, etc. geometry feature of chip shape image and thing of those features as inputting vector of neural network. Adopt radbas neural network and training the network using RLS.

研究了径向基函数神经网络在硬质合金刀具切屑形态图像识别中的应用，提出了面积比、欧拉数、分散度等硬质合金刀具切屑形态图像的几何特征，以上述特征作为神经网络的输入矢量，利用径向基函数网络，采用了递推最小二乘法训练该网络。

The experimental data were trained by BP neural network, and the results were curve fitted to set up a fitting function which was used in the genetic algorithm process to reach the optimum.

首先利用BP神经网络来训练已有实验值，然后将训练后的神经网络作为知识源，通过曲线拟合与逼近求得设计变量与目标函数值的函数关系表达式，最后将这一函数表达式作为遗传算法的适应度函数进行遗传迭代寻找最优解。

This method uses the strong non-linear mapping ability which the RBF network has and its short-time training merit to construct the network, substitutes the non-analytic function, make it to instate of the optimized question of the objective function, and iterates this objective function with the genetic algorithm to search the optimal solution.

该方法利用RBF网络所具有的非线性映射能力强，训练时间短的优点，构建网络，替代非解析函数，使之作为优化问题的目标函数，并用遗传算法搜索迭代出该目标函数的最优解。

There are complex variations in realistic low-voltage power line network topology framework.In order to study the low-voltage power line transmission channel model,a model to describe the power line network channel topology framework is established in terms of basic characteristics of low-voltage power line network in this paper.

低压电力线网络拓扑结构变化复杂，为了研究低压电力线信道传输模型，根据低压电力线网络的基本特点建立了描述电力线网络拓扑结构的模型，利用模型把低压电力信道作为一个过程去描述，建立了节点信号传输函数来推导低压电力线网络的传递函数。

In chapter 2, we firstly introduce the model of a discrete-time neural network with generalized input-output function. The model generalizes the input-output function in transiently chaotic neural network to a class of continuous, differentiable and monotone increasing functions. Secondly we study the uniformly asymptotical stability of equilibrium in the non-autonomous model. Finally, several examples and numerical simulations are given to illustrate and reinforce our theories. In chapter 3, we firstly introduce a specific class of discrete-time neural network models with sinusoidal activation function.

在本文的第二章中，首先介绍了一类具有广义输入输出函数的非自治离散神经网络模型，该模型把瞬时混沌神经网络模型中的输入输出函数推广到了一般的单调递增且连续可微的函数；其次，利用Schauder不动点原理和利用Lyapunov函数逆定理依次证明了模型平衡点的存在性和该模型在时变权值下的一致渐近稳定性；最后，对几个具体的例子进行数值模拟，数值模拟的结果更好地说明了我们的结论。

The model generalizes the input-output function in transiently chaotic neural network to a class of continuous, differentiable and monotone increasing functions. Secondly we study the uniformly asymptotical stability of equilibrium in the non-autonomous model. Finally, several examples and numerical simulations are given to illustrate and reinforce our theories. In chapter 3, we firstly introduce a specific class of discrete-time neural network models with sinusoidal activation function.

在本文的第二章中，首先介绍了一类具有广义输入输出函数的非自治离散神经网络模型，该模型把瞬时混沌神经网络模型中的输入输出函数推广到了一般的单调递增且连续可微的函数；其次，利用Schauder不动点原理和利用Lyapunov函数逆定理依次证明了模型平衡点的存在性和在时变权值下的一致渐近稳定性；最后，对几个具体的例子进行数值模拟，数值模拟的结果更好地说明了我们的结论。

An Ellipsoidal Basis Function can make the partition of input space and make a limitary and bounded.

椭球基函数（Ellipsoidal Basis Function，EBF）使网络划分输入空间成为封闭有界的局部作用的空间，与径向基函数（Radial Basis Function，RBF）神经网络的高斯函数相比，它对空间的划分更明确。

Neither the killing of Mr Zarqawi nor any breakthrough on the political front will stop the insurgency and the fratricidal murders in their tracks.

在对危险的南部地区访问时，他斥责什叶派民兵领导人对中央集权的挑衅行为。

In fact,I've got him on the satellite mobile right now.

实际上 我们已接通卫星可视电话了