基于RBF神经网络的一类非线性时滞系统自适应控制器设计

针对一类带有未知非线性函数的严格反馈非线性时滞系统,设计了一种自适应神经网络控制器.选择径向基函数神经网络逼近未知的非线性函数.所提出的控制方案能保证闭环系统的所有信号是全局一致最终有界的.证明了跟踪误差信号将收敛于一个小紧集内.仿真实例验证了所提出方法的有效性.     

符号函数的Legendre非线性逼近

1引言许多数学和物理工作者研究了逼近形式正交多项式级数的具有较好收敛性的非线性方法,如文献[2-5,9]．这些非线性逼近方法的一个共同点是使用了线性级数中正交多项式的母函数．众所周知,的符号函数具有很多的应用,如文献[7]利用符号函数的积分表示来分析相联存储器的回想过程．文献[1]及其中所引用的一些文献为了获得交迭格Dirac算子,讨论了符号函数的有理逼近和连分式展开．在本文中,我们研究符号函数的Lengendre     

Galois环和Z/(m)环上完全非线性函数的性质

本文把完全非线性函数推广到了有限Abel群上,利用特征谱讨论了Z/(m)上Bent函数与GF(pe)上bent函数以及完全非线性函数定义之间的关系;给出Galois环与Z/(m)上最佳线性逼近的特征谱表示,得到完全非线性函数在某种程度上能抵抗最佳线性逼近攻击的结论;并给出一种Galois环与Z/(m)环上完全非线性函数的构结方法.     

非线性l1问题的光滑近似算法

为非线性l1问题的求解构造了光滑逼近函数.首先将非线性l1问题转化为等价的不可微优化问题;其次通过两步提出光滑逼近函数的一般性构造方法;最后进行了数值仿真.文中介绍了光滑逼近函数的有关性质,指出相关文献已有的光滑函数方法是本文的特例,并证明了方法的收敛性及有效性.     

求解非线性Black-Scholes模型的自适应小波精细积分法

针对非线性Black-Scholes方程,基于quasi-Shannon小波函数给出了一种求解非线性偏微分方程的自适应多尺度小波精细积分法.该方法首先利用插值小波理论构造了用于逼近连续函数的多尺度小波插值算子,利用该算子可以将非线性Black-Scholes方程自适应离散为非线性常微分方程组;然后将用于求解常微分方程组的精细积分法和小波变换的动态过程相结合,并利用非线性处理技术(如同伦分析技术)可有效求解非线性Black-Scholes方程.数值结果表明了该方法在数值精度和计算效率方面的优越性.     

随机设计变量情形回归函数的非线性小波估计 *

在随机设计变量情形 ,构造了回归函数的非线性小波估计以及自适应非线性小波估计 .证明了非线性小波估计在Besov空间中可达到最优收敛速度 ,自适应非线性小波估计在一大类Besov空间中可达到次最优收敛速度 ,即和最优收敛速度只相差lnn .这样 ,在随机设计变量情形 ,所构造的回归函数的非线性小波估计和在固定设计点下对回归函数所构造的非线性小波估计几乎具有相同的优良性质 .进一步 ,只要求误差有有界三阶矩 ,而不要求误差服从正态分布 .     

小波尺度函数计算的广义高斯积分法及其应用

对于小波尺度函数变换的分解系数的积分运算建立了以尺度函数为权的广义高斯积分方法的运算格式．借助于样条函数,证明了其广义高斯积分随小波分解水平（resolutionlevel）指标的上升而收敛．在此基础上给出了以小波尺度函数变换重构或逼近任一函数的显式解析式,并对具有函数算子、微分或积分算子的运算给出了变换规则．这对于求解复杂非线性方程（组）是一种强有力的工具．最后给出了用该文方法求解非线性二点边值问题的算例．     

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。     

基于增强型模糊神经网络的盲均衡算法研究

提出一种利用增强型模糊神经网络进行盲均衡的新算法.增强型模糊神经网络具有很好的非线性逼近能力和映射能力,符合非线性通信技术处理的特点.给出增强型神经网络的结构和状态方程,提出代价函数,推导出均衡参数的迭代公式.仿真表明,本算法收敛后误码率减减小,收敛效果较好.     

一类递归小波神经网络的稳定性研究

在小波神经网络（WNNs）和递归神经网络（RNNs）的基础上,提出了一类递归小波神经网络（RWNNs）模型,它具有两种网络模型的优点A·D2根据Liapunov渐近稳定理论,对该模型的渐近稳定性进行了研究,并给出了相关的定理和公式．仿真结果表明该模型对非线性动态系统有良好的辨识效果．     

On the near optimality of the stochastic approximation of smooth functions by neural networks

We consider the problem of approximating the Sobolev class of functions by neural networks with a single hidden layer, establishing both upper and lower bounds. The upper bound uses a probabilistic approach, based on the Radon and wavelet transforms, and yields similar rates to those derived recently under more restrictive conditions on the activation function. Moreover, the construction using the Radon and wavelet transforms seems very natural to the problem. Additionally, geometrical arguments are used to establish lower bounds for two types of commonly used activation functions. The results demonstrate the tightness of the bounds, up to a factor logarithmic in the number of nodes of the neural network. This revised version was published online in June 2006 with corrections to the Cover Date.     

The construction and approximation of some neural networks operators

In this paper,the technique of approximate partition of unity is used to construct a class of neural networks operators with sigmoidal functions.Using the modulus of continuity of function as a metric,...     

Nonparametric nonlinear regression using polynomial and neural approximators: a numerical comparison

The solution of nonparametric regression problems is addressed via polynomial approximators and one-hidden-layer feedforward neural approximators. Such families of approximating functions are compared as to both complexity and experimental performances in finding a nonparametric mapping that interpolates a finite set of samples according to the empirical risk minimization approach. The theoretical background that is necessary to interpret the numerical results is presented. Two simulation case studies are analyzed to fully understand the practical issues that may arise in solving such problems. The issues depend on both the approximation capabilities of the approximating functions and the effectiveness of the methodologies that are available to select the tuning parameters, i.e., the coefficients of the polynomials and the weights of the neural networks. The simulation results show that the neural approximators perform better than the polynomial ones with the same number of parameters. However, this superiority can be jeopardized by the presence of local minima, which affects the neural networks but does not regard the polynomial approach.     

Approximating smooth and sparse functions by deep neural networks: Optimal approximation rates and saturation

Constructing neural networks for function approximation is a classical and longstanding topic in approximation theory. In this paper, we aim at constructing deep neural networks with three hidden layers using a sigmoidal activation function to approximate smooth and sparse functions. Specifically, we prove that the constructed deep nets with controllable magnitude of free parameters can reach the optimal approximation rate in approximating both smooth and sparse functions. In particular, we prove that neural networks with three hidden layers can avoid the phenomenon of saturation, i.e., the phenomenon that for some neural network architectures, the approximation rate stops improving for functions of very high smoothness.     

Approximation by radial bases and neural networks

In this paper, we study approximation by radial basis functions including Gaussian, multiquadric, and thin plate spline functions, and derive order of approximation under certain conditions. Moreover, neural networks are also constructed by wavelet recovery formula and wavelet frames.     

The new approximation operators with sigmoidal functions

The aim of this paper is to investigate approximation operators with logarithmic sigmoidal function of a class of two neural networks weights and a class of quasi-interpolation operators. Using these operators as approximation tools, the upper bounds of estimate errors are estimated for approximating continuous functions.     

Constructive Approximation by Superposition of Sigmoidal Functions

In this paper, a constructive theory is developed for approximating functions of one or more variables by superposition of sigmoidal functions. This is done in the uniform norm as well as in the $L^p$ norm. Results for the simultaneous approximation, with the same order of accuracy, of a function and its derivatives (whenever these exist), are obtained. The relation with neural networks and radial basis functions approximations is discussed. Numerical examples are given for the purpose of illustration.     

Triply fuzzy function approximation for hierarchical Bayesian inference

We prove that three independent fuzzy systems can uniformly approximate Bayesian posterior probability density functions by approximating the prior and likelihood probability densities as well as the hyperprior probability densities that underly the priors. This triply fuzzy function approximation extends the recent theorem for uniformly approximating the posterior density by approximating just the prior and likelihood densities. This approximation allows users to state priors and hyper-priors in words or rules as well as to adapt them from sample data. A fuzzy system with just two rules can exactly represent common closed-form probability densities so long as they are bounded. The function approximators can also be neural networks or any other type of uniform function approximator. Iterative fuzzy Bayesian inference can lead to rule explosion. We prove that conjugacy in the if-part set functions for prior, hyperprior, and likelihood fuzzy approximators reduces rule explosion. We also prove that a type of semi-conjugacy of if-part set functions for those fuzzy approximators results in fewer parameters in the fuzzy posterior approximator.     

基于非线性混沌时序动力系统的预测方法研究

主要研究由混沌时序所确定的非线性动力系统的预测方法．研究了非线性自相关混沌模型的结构,模型阶数的确立技术．将神经网络和小波理论相结合,研究了小波变换神经网络的结构,给出了小波神经网络的学习方法;提出了一种新的基于小波网络的参数辨识方法．该方法可以有选择地提取时序中的不同的时间、频率尺度,实现原时序的趋势或细节预测．通过对混沌时序进行预处理,并比较预处理后的预测结果,得到了一些有益的结果:用非线性自相关混沌模型采用小波网络对模型参数进行辨识,其辨识的准确程度较高,用该模型对混沌时序(包括含有噪声)的预测比较有效．     

Biorthogonal Locally Supported Wavelets on the Sphere Based on Zonal Kernel Functions

This article presents a method for approximating spherical functions from discrete data of a block-wise grid structure. The essential ingredients of the approach are scaling and wavelet functions within a biorthogonalisation process generated by locally supported zonal kernel functions. In consequence, geophysically and geodetically relevant problems involving rotationinvariant pseudodifferential operators become attackable. A multiresolution analysis is formulated enabling a fast wavelet transform similar to the algorithms known from classical tensor product wavelet theory.