L~p(R~n)中的神经网络逼近和系统识别

本文主要研究函数的叠加对Ｌ~ｐ（Ｒ~ｎ）中的函数,Ｌ~ｐ（Ｒ~ｎ）上的非线性连续泛函及非线性连续算子的逼近这些问题与Ｓｉｇｍａ－Ｐｉ型神经网络逼近能力有关。     

黎曼相关积分研究

通过证明和反例讨论黎曼积分、直接黎曼积分、黎曼-斯蒂尔切斯积分三者间的联系与区别.结果显示：若函数直接黎曼可积,则它黎曼可积,并且两者积分值相同,但反之不成立;若函数黎曼可积,则任意连续函数关于该函数不一定黎曼-斯蒂尔切斯可积.从讨论结果中还获得直接黎曼可积和黎曼可积各自的一个充分条件.     

有限交换环上极限线性群的Sylowp—子群

本文给出了有限交换局部环Ｒ上无限线性群ＧＬ（Ｒ）＝∪ｎＧＬｎＲ的Ｓｙｌｏｗｐ－子群的形式．令Ｍ是有限交换局部环Ｒ的唯一极大理想，ｋ＝Ｒ／Ｍ为Ｒ的剩余类域．用Ｘ（ｋ）表示ｋ的特征，并假定Ｐ与ｘ（ｋ）互素．作者证明了：ＧＬ（Ｒ）的任一Ｓｙｌｏｗｐ－子群Ｓ或者同构于的可数无限直积与Ｐ（ｊ）的无限直积的直积（当Ｐ≠２或Ｐ＝２，Ｘ（ｋ）β≡１（ｍｏｄ４））或者同构于Ｐｉ的无限直积与Ｐ（ｊ）的无限直积的直积（当Ｐ＝２，Ｘ（ｋ）β≡３（ｍｏｄ４）），这里，只是ＧＬ（ｅｐｉ）Ｒ（分别地，ＧＬ（２ｒｉ）Ｒ）的Ｓｙｌｏｗｐ－子群，Ｐ（ｊ））同构于Ｐ＝∪ｉ∈Ｉｐｉ，Ｉ是可数集．     

复合函数黎曼可积性的讨论

本文利用有界函数黎曼可积的充要条件讨论了某些复合函数的黎曼可积性,给出了外函数黎曼可积,内函数连续,复合函数不一定黎曼可积的例子．     

非绝对积分概论(连载三)

Ⅱ非绝对积分及其性质§３Ｌ－积分、反常Ｒ－积分与ＫＨ－积分之关系前面我们已经看到,ＫＨ－可积函数类确比Ｌ－可积函数类广泛．例２．１４说明了反常Ｒ－可积函数也是ＫＨ－可积的．这一节我们将从理论上直接证明反常Ｒ－积分、Ｌ－积分都为ＫＨ－积分的特殊情况．首...     

黎曼可积函数列的极限理论及应用

对黎曼可积函数列的极限函数的可积性进行讨论．运用黎曼积分自身的理论依次证明了：一致收敛函数列的极限函数的黎曼可积性,黎曼积分下的控制收敛定理和广义积分下的控制收敛定理。并给出了一些应用例子．     

黎曼积分的完备化

综述了黎曼可积函数的基本特征,并指出黎曼可积函数列的极限运算在积分意义下是不封闭的.在构造了完备化空间之后,证明了该空间就是勒贝格可积函数空间,从而说明了黎曼积分的完备化形式是勒贝格积分.     

函数的原函数存在与黎曼可积的关系

本文讨论原函数存在与黎曼可积之间的联系与区别,通过列举具体的函数来说明函数的原函数存在与黎曼可积是相互独立的概念,两者之间是互不蕴舍的关系.     

函数可积与原函数存在的关系

详细探讨函数黎曼可积性与原函数存在性之间的相互关系,通过构造具体函数说明黎曼可积与原函数存在是相互独立形成的不同概念,它们之间是互不蕴含的关系.     

具有周期输入Hopfield型神经网络的全局渐近性质

在不假定非线性激励函数有界和可微的条件下,应用Mawhin的重合度理论及Liapunov函数法给出一类具有周期输入的Hopfield型神经网络存在周期解及其全局指数稳定的充分条件。     

Universality of deep convolutional neural networks

Deep learning has been widely applied and brought breakthroughs in speech recognition, computer vision, and many other domains. Deep neural network architectures and computational issues have been well studied in machine learning. But there lacks a theoretical foundation for understanding the approximation or generalization ability of deep learning methods generated by the network architectures such as deep convolutional neural networks. Here we show that a deep convolutional neural network (CNN) is universal, meaning that it can be used to approximate any continuous function to an arbitrary accuracy when the depth of the neural network is large enough. This answers an open question in learning theory. Our quantitative estimate, given tightly in terms of the number of free parameters to be computed, verifies the efficiency of deep CNNs in dealing with large dimensional data. Our study also demonstrates the role of convolutions in deep CNNs.     

Interpolation and rates of convergence for a class of neural networks

This paper presents a type of feedforward neural networks (FNNs), which can be used to approximately interpolate, with arbitrary precision, any set of distinct data in multidimensional Euclidean spaces. They can also uniformly approximate any continuous functions of one variable or two variables. By using the modulus of continuity of function as metric, the rates of convergence of approximate interpolation networks are estimated, and two Jackson-type inequalities are established.     

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.     

具有随机隐单元的渐增前馈神经网络的$L^2(R^d)$逼近能力

This paper studies approximation capability to L2(Rd) functions of incremental constructive feedforward neural networks(FNN) with random hidden units.Two kinds of therelayered feedforward neural networks are considered:radial basis function(RBF) neural networks and translation and dilation invariant(TDI) neural networks.In comparison with conventional methods that existence approach is mainly used in approximation theories for neural networks,we follow a constructive approach to prove that one may simply randomly choose parameters of hidden units and then adjust the weights between the hidden units and the output unit to make the neural network approximate any function in L2(Rd) to any accuracy.Our result shows given any non-zero activation function g :R+→R and g(x Rd) ∈ L2(Rd) for RBF hidden units,or any non-zero activation function g(x) ∈ L2(Rd) for TDI hidden units,the incremental network function fn with randomly generated hidden units converges to any target function in L2(Rd) with probability one as the number of hidden units n→∞,if one only properly adjusts the weights between the hidden units and output unit.     

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。     

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.     

前馈神经网络和Logit回归的比较研究

近年来 ,前馈神经网络广泛地应用在 Logit回归作为标准统计方法的分析领域 .但却很少作它们之间的直接比较 ,本文是 Logit回归和前馈神经网络“比较研究”的一个尝试 ,说明了一些理论结果和特性 ,讨论了在它们的应用中碰到的一些实际问题 ,还进一步用分析的和模拟的两种方法研究了一些重要的渐近概念、过分拟合以及模型选择等问题 ,最后讨论并给出一些结论     

单个函数平移和伸缩的叠加在L~p(R~d)中的逼近(英)

本文主要讨论单个函数平移和伸缩的线性组合对Lp（Rn）中任一紧集内函数的逼近．给出一个很强的逼近结果．这在神经网络应用研究中具有重要意义．     

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.     

分段线性神经网络的逼近理论

随着分段线性函数的广泛应用,本文尝试研究浅层和深层的分段线性神经网络的逼近理论.作者将应用于三层感知机模型的万能逼近定理拓展到分段线性神经网络中,并给出与隐藏神经元个数相关的逼近误差估计.利用分段线性函数构造锯齿函数的显式方法,证明解析函数可以通过分段线性神经网络的深度堆叠以指数速率逼近,并辅以相应的数值实验.