神经网络

And then, the GFNN (generalized fuzzy neural network) is put forwand, the GFNN approximation theorem is proved.

从非线性系统本身的物理背景出发，根据系统本身的内在特性、先验知识和经验建立系统辨识模型，提出了广义模糊神经网络。

Since the structure self-organization and self-learning abilities of GFNN, it is different from the universal approximation theorem of FLS and BP theorem of NN.

由于GFNN的结构自组织和参数自学习能力，使得它与模糊逻辑系统中的万能逼近定理以及人工神经网络的BP逼近定理不同，GFNN不再只是一个存在性定理，它给出了GFNN的实现过程。

The approximation theorem of the rough neural network is proved. Then the method is applied to the fault verification of fighter plane, the simulation results show that the rough neural network is efficient.

最后将此方法应用于歼击机的故障认定系统，仿真结果表示，此粗糙神经网络可以很好地对具有区间数的歼击机故障认定系统进行故障认定。

Wang-type fuzzy logic system and its functional approximation ability are researched deeply, A class of Gauss-type fuzzy logic system is presented and studied What it defers from Wang-type fuzzy logic system is its using Gauss fuzzifier The analytical expression of this fuzzy logic system is derived detailed Its universal approximation theorem for nonlinear functions is proved by StoneWeiestrass theorem.

通过对两类模糊系统作为非线性辨识器的仿真研究显示出高斯型模糊逻辑系统在抗数据干扰方面比Wang型模糊系统有优势。对非线性动态系统的辨识问题，借助递归神经网络的研究成果，提出一种基于递归网络结构的自适应模糊逻辑系统和参数学习算法。

A function approximator like an ANN can be viewed as a black box, and when it comes to FANN, this is more or less all you will need to know.

像一个神经网络函数逼近可以被看作是一个黑盒子，当它来到范，这是或多或少所有您需要知道的。

Thanks to robust nonlinear approximate function and computational cost, a feed-forward neural network as optimal approximator is employed.

考虑算法的非线性逼近能力和计算速度，采用了神经网络作为优化求解器。

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。

The states of system and the faults in system are estimated simultaneously. The inputs of the fault approximator are the estimated states.

首先提出一种状态估计器设计方法；然后在进行状态估计的同时用RBF神经网络来逼近系统所发生的故障。

One of the key issues in the design of fault diagnosis scheme is the effect of modelling uncertainties and disturbances. By using neural networks observer or approximator, the fault detection and diagnosis strategy for a class of nonlinear systems with modelling uncertainties are investigated.

而非线性系统故障诊断算法的鲁棒性则是一个极其关键的问题，本文主要针对非线性系统，进行了基于神经网络的鲁棒故障诊断方法研究。

Using the RBF neural network approximator, the main assumption of the first approach is that the minimal approximation errors satisfy certain bounding conditions.

利用RBF神经网络逼近器，第一种方法主要的假设是最小逼近误差满足确定有界条件。

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。