前向正则模糊神经网络依K-积分模的泛逼近能力

针对前向正则模糊神经网络引进K-拟可加积分和K-积分模概念,应用积分转换定理研究了该网络在K-积分模意义下对模糊值简单函数类的泛逼近能力,进而在有限K-拟可加测度空间上,借助模糊值简单函数为桥梁获得了前向正则模糊神经网络依K-积分模对(u)-可积有界模糊值函数类仍具有泛逼近性.该结果表明前向正则模糊神经网络对连续模糊系统的逼近能力可以推广为对一般可积系统的逼近能力.     

拟可加测度空间上广义Sugeno积分的收敛性

在拟可加测度空间上通过引入拟乘算子重新定义广义Sugeno积分,针对依拟可加测度收敛的函数列,应用诱导算子和拟乘算子的运算性质讨论和分析广义Sugeno积分的收敛性,进而获得了这种广义Sugeno积分的单调增收敛定理.     

模糊正则文法的逼近性

为了扩大现有研究的应用范围,基于max-min型模糊正则文法引入了max-*型模糊正则文法(其中*为特定t-模)的概念,讨论了max-*型模糊正则文法可以通过max-min型模糊正则文法在任意给定的逼近精度来逼近.研究表明,当t-模*满足一定的条件时,max-*型模糊正则文法与max-min型模糊正则文法在生成模糊语言能力方面是等价的.     

K-拟可加模糊值积分的双零渐近可加与穷竭性

针对已经建立的K-拟可加模糊值积分,将这种积分整体看成可测空间上取值于模糊数值的集函数。应用其转换定理和诱导算子的性质,获得了这种模糊积分不仅具有双零渐近可加性,而且也满足穷竭性。这些特性对于描述模糊值可测函数列和模糊积分序列的收敛性具有重要的意义。     

具有函数的泛逼近性能的模糊控制器的设计

构造出9类具有函数的泛逼近性能的模糊控制器,这些模糊控制器均由模糊蕴涵算子构造而成.利用倒车仿真说明采用具有函数的泛逼近性能的模糊控制器可以用于实际的模糊控制系统中.     

关于K-拟可加模糊积分的几点注记

在K-拟可加模糊积分定义及积分转换定理的基础上，证明这种模糊积分恰好构成K-拟可加模糊测度，并依据积分转换定理讨论这种K-拟可加模糊积分的一些补充性质。     

基于σ-λ律的Sugeno测度及其可加性误差估计

讨论基于σ-λ律的Sugeno测度的刻划定理,借助于所提出的刻划定理。给出基于σ-λ律的Sugeno测度可列可加的误差估计及其计算公式。     

Choquet积分的收敛定理

Murofushi、Sugeno等学者已对关于模糊测度的Choquet积分进行了详细的研究,但关于积分的收敛理论是不够的。本文讨论这一问题,给出Choquet积分的一些收敛定理,包括广义单调收敛定理、Fatou引理等。从中可以看出,Choquet积分与Sugeno模糊积分具有相同的收敛定理。     

基于输入-输出数据的重心法模糊系统及其泛逼近性

研究基于输入-输出数据的重心法模糊系统及其泛逼近性.首先,将一组单输入-单榆出数据转换成模糊推理规则,通过选择适当的模糊蕴涵算子生成模糊关系,再利用这种模糊关系求出二雄随机变量的联合概率密度函数.当将模糊蕴涵分别取为Larsen蕴涵和Mamdani蕴涵时,分别得到了两种具体的概率密度函数(称之为Larsen分布和Mamdani分布).其次,利用这两种概率分布.分别求出了对应的两种回归函数,指出这种回归函数实际上是模糊控制中的重心法模糊系统.我们分别给出了这种模糊系统具有泛逼近性的充分条件.从而进一步揭示了模糊系统的概率论意义.     

前向网络作为模糊函数泛逼近器的一致性分析

前向神经网络的泛逼近性一直是神经网络的研究热点.本文给出了连续模糊函数的定义,依Hausdorff度量,借助模糊值Bernstein多项式关于连续模糊函数的逼近性质,证明了前向网络作为模糊函数泛逼近器的一致逼近性结果,并通过实例给出了逼近性的具体实现过程.     

Approximation Methods by Regular Functions

This paper is a survey of approximation results and methods by smooth functions in Banach spaces. The topics considered in the paper are the following: approximation by polynomials by C^k-functions using the method of smooth partitions of unity, approximation by the fine topology, analytic approximation and regularization in Banach spaces using the infimal convolution method.     

Measure Theoretic Results for Approximation by Neural Networks with Limited Weights

In this article, we study approximation properties of single hidden layer neural networks with weights varying in finitely many directions and with thresholds from an open interval. We obtain a necessary and simultaneously su?cient measure theoretic condition for density of such networks in the space of continuous functions. Further, we prove a density result for neural networks with a specifically constructed activation function and a fixed number of neurons.     

Neural Networks for Optimal Approximation of Continuous Functions on the Unit Sphere

We prove that, to approximate continuous target functions defined on the unit sphere of ${\mathbb{R}^d}$ , neural networks are at least as good as algebraic polynomials.     

On Approximation by Neural Networks with Optimized Activation Functions and Fixed Weights

Recently, Li [16] introduced three kinds of single-hidden layer feed-forward neural networks with optimized piecewise linear activation functions and fixed weights, and obtained the upper and lower bound estimations on the approximation accuracy of the FNNs, for continuous function defined on bounded intervals. In the present paper, we point out that there are some errors both in the definitions of the FNNs and in the proof of the upper estimations in [16]. By using new methods, we also give right approximation rate estimations of the approximation by Li’s neural networks.     

三层前向神经网络的一致逼近性

近年来，前向神经网络泛逼近的一致性分析一直为众多学者所重视。本文系统分析三层前向网络对于拟差值保序函数族的一致逼近性，其中，转换函数σ是广义Sigmoidal函数。并将此一致性结果用于建立一类新的模糊神经网络(FNN)，即折线FNN．研究这类网络对于两个给定的模糊函数的逼近性，相关结论在分析折线FNN的泛逼近性时起关键作用。     

球面神经网络的构造与逼近

研究球面神经网络的构造与逼近问题.利用球面广义的de la Vallee Poussin平均、球面求积公式及改进的单变量Cardaliaguet-Euvrard神经网络算子,构造具logistic激活函数的单隐层前向网络,并给出了Jackson型误差估计.     

Computing the Approximation Error for Neural Networks with Weights Varying on Fixed Directions

We obtain a sharp lower bound estimate for the approximation error of a continuous function by single hidden layer neural networks with a continuous activation function and weights varying on two fixed directions. We show that for a certain class of activation functions this lower bound estimate turns into equality. The obtained result provides us with a method for direct computation of the approximation error. As an application, we give a formula, which can be used to compute instantly the approximation error for a class of functions having second order partial derivatives.