查询词典 universal

Neural networks is viewed as a universal approximator for nonlinear functions, but there are some fatal bugs with it, so it is necessary to find another method more right for neutralization process.

神经网络是目前中和过程非线性系统建模中常用的一种建模方法，但本身具有一些难以克服的缺陷降低了它的发展和应用效果，因此寻求更适于中和过程非线性系统建立模型的理论及方法是十分必要的。

This paper presents that FCP network model and improved T-S model used in the disquisition are universal approximator, with the latter proved.

本文指出文中用到的FCP网络模型和改进T-S模型为通用逼近器，同时给出后者的证明。

The thesis makes a preliminary exploration of the necessary conditions for fuzzy logic systems as universal approximator for nonlinear function, which is an important theoretical problem of fuzzy logic systems.

这一研究的重要意义在于，我们是在一个统一的框架下来对模糊逻辑系统的这一理论问题进行研究的，是这一研究领域开创性成果。

Prove that this kind of fuzzy inference model is an universal approximator, and proposed one method identifying this fuzzy model from training data set.

提出了带概率因子的模糊推理模型，证明了该种模糊推理系统是一个通用逼近器，并给出了一种从训练数据集中辨识该模糊模型的方法。

The characteristics of B|spline basis function is first discussed, based on which B|spline neural network is proved to be a universal approximator.

1引言对于一个给定的非线性函数，我们都知道用神经网络可以以任意的精度来逼近它，原因就是神经网络是全局逼近器［1］。

Finally a generalized fuzzy hyperbolic model is proposed, which is proven to be a universal approximator, and two identification algorithms are derived.

最后提出一种广义模糊双曲正切模型，并证明了此模型具有全局逼近性。

By this way, the obstacles are removed for the research on the theoretical problems of adaptive fuzzy logic system in a unitary frame, for instance the problem of the general fuzzy logic system as universal approximator of nonlinear function.

在概念上明确了专家信息的本质特征可以看作是来自语言的模糊信息，为通过自适应模糊逻辑系统对专家信息的研究和利用打开了通道。

Moreover, we propose the conservatism compared theorem of sufficient condition of SISO Mamdani fuzzy system as universal approximator obtained by three different algorithms.

从输入输出数据中设计模糊系统是一个重要的问题，在各种控制、信号处理和通讯系统中得到了广泛的应用。

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。

A new generalized fuzzy hyperbolic model is proposed, which can be seen as the generalization of common fuzzy hyperbolic model. The generalized fuzzy hyperbolic model is proven to be a universal approximator. Two identification algorithms are put forward to identify the model from input/out data.

通过对模糊双曲正切模型的改进，提出一种广义模糊双曲正切模型，证明了此模型可以以任意精度逼近紧集上的连续非线性函数，即此模型具有全局逼近性，并给出其辨识算法。

In the chapter 2, the theoretic knowledge about the photosensitive resin and the grinding tools was firstly introduced.

第二章阐述了光固化树脂结合剂磨具的相关理论研究。

Do not use the program's indenting or margin-setting features; these will be added during typesetting.

不要使用缩排，页面边缘设置之类的选项，偶看不大懂。