网络函数

RBF networks have several following advantages: being a best universal approximator, having rapid learning speed and a compact topological structure.

径向基函数网络被认为是通用的函数逼近子并具有快速的学习能力和紧致的拓扑结构等优点。

In Chapter Two, Liapunov functional method and Liapunov function method with Razumikhin techniques are employed to obtain some delay independent stability results for the Cohen-Grossberg neural networks with multiply delays.

在第三章中，我们首先对一般的无时滞Cohen-Grossber神经网络模型建立了几个稳定性定理，即文中定理3.3.1-3.3.4。从其中推论可看出负的自联接起着很大的稳定化网络的作用。然后我们考虑了一般的Hopfiel神经网络模型，运用单调动力系统理论，在对激发函数做出很弱的假定下获得了与时滞相关的稳定性结果，并对时滞的大小给出很多的估计，文中定理3.4.3。

Based on analyzing regression analysis, neural network and the least square support vector machines that the three soft computing methods fitting for data fitting, in the paper try to use nonlinear regression analysis, the BP neural network based on Levenberg-Marquardt training algorithm, radial basis function neural network on orthogonal least square training algorithm and least square support vector machines for tracking the position of glass plate.

本文在分析适于数据拟合的回归分析、神经网络、最小二乘支持向量机这三种"软计算"方法的基础上，尝试将非线性回归分析方法，基于Levenberg-Marquardt算法的BP神经网络，基于正交最小二乘训练算法的径向基函数神经网络和最小二乘支持向量机应用于玻璃板位的跟踪中。

The simulation results show the good performance for the system by using network to adjust the parameters and the recurrent weight of neural network on-line dynamically on the condition of variety of system parameter and the impact of outside uncertainty factors.

仿真结果表明，当系统参数动态变化或受到外部不确定因素影响时，利用神经网络来在线调整网络的隶属函数参数以及神经网络递归权值，使系统具有良好的动、静态性能。

We proposed a simple way to calculate separability of each class after radical basis function neural networks have been selected as a type of node.

使用径向基函数网络作为节点网络，使节点网络结构适应两类间的可分性，从而最终优化了神经树网络的结构。

The Radical asis Function Neural Network is a feed-forward NN model with the capacity of local approximation, so it can be used as a multiple-user detector in the CDMA.

径向基函数神经网络是一种具有局部逼近能力的前向神经网络模型，它可用作码分多址中的多用户检测器，并具有较好的检测性能；但是存在不足，主要表现在网络的构造和训练算法的优化方面。

The strategy of decomposition and coordination is proposed based on the resolvability of HEN's exergy-economic objective function, which is between optimizaition of network and optimization of mach units.

在换热网络目標函数可分解性的基础上，本文又进一步提出了换热网络分解协调优化的研究策略，它是在各个匹配单元和整个换热网络结构之间进行优化协调，並获得换热网络的最优结构和各匹配单元的最优操作参数。

Differing from the feed-back error compensation method, the selflearning error pre-compensation method offered by the paper is based on both ANN and time series technique to obtain the error pre-compensating curve using the non-linear ANN pre-compensation model. Because of the self-learning character of the ANN, this new type of precompensation model can be self-adjusted.

与常规的反馈补偿方法不同，本文提出的自学习误差预测补偿方法，将时间序列预测与神经网络的自学习自适应优化建模技术相结合，利用神经网络非线性预测模型产生误差预补偿函数，并利用神经网络的自学习特性对所建预测模型进行修正，所以这种新型的误差补偿方法能够获得更高的误差补偿精度和控制速度，简单实用，适于推广，具有生产应用价值。

The tight wavelet neural network was constituted taking the nonlinear Morlet wavelet radices as the stimulant function. The idiographic algorithm was presented. It can combine the advantages of wavelet analysis and neural networks.

以非线性Morlet小波基作为激励函数，形成神经元，结合小波变换与神经网络各自的优点，建立集小波分析与神经网络于一体的紧致型小波神经网络，并给出了具体的算法。

On the basis of the algorithm of BP neural network,the network's excitation function has been improved, and an ANN-based Seismic Response recognising system for pile foundation bridge pier has been developed according to the characters of the seismic response of the pier.

在原BP神经网络基本算法的基础上，按研究桩基桥墩地震响应的特点，改进了网络的激励函数，开发了适用于桩基桥墩地震响应的神经网络辨识系统。

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