模糊神经网络理论研究综述

本文对于近年来受到普遍重视的前向模糊神经网络及有反馈的模糊神经网络的性质、学习算法及应用等方面的研究进行了较为详尽的综述，分析了所取得的主要成果及其特点，并指出了今后模糊神经网络理论研究中有待解决的许多问题。     

Robust Simulation-Based Estimation of ARMA Models

This article proposes a new approach to the robust estimation of a mixed autoregressive and moving average (ARMA) model. It is based on the indirect inference method that originally was proposed for models with an intractable likelihood function. The estimation algorithm proposed is based on an auxiliary autoregressive representation whose parameters are first estimated on the observed time series and then on data simulated from the ARMA model. To simulate data the parameters of the ARMA model have to be set. By varying these we can minimize a distance between the simulation-based and the observation-based auxiliary estimate. The argument of the minimum yields then an estimator for the parameterization of the ARMA model. This simulation-based estimation procedure inherits the properties of the auxiliary model estimator. For instance, robustness is achieved with GM estimators. An essential feature of the introduced estimator, compared to existing robust estimators for ARMA models, is its theoretical tractability that allows us to show consistency and asymptotic normality. Moreover, it is possible to characterize the influence function and the breakdown point of the estimator. In a small sample Monte Carlo study it is found that the new estimator performs fairly well when compared with existing procedures. Furthermore, with two real examples, we also compare the proposed inferential method with two different approaches based on outliers detection.     

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.     

加权平衡指数损失函数下的广义信度保费估计

在非寿险中,在索赔经历虽然相互独立,但有时会服从不同的分布.通过考虑保费的目标估计来对风险保费进行了研究,并采用正交投影的方法得到了目标问题的最优解,从而得到了加权平衡指数损失函数下的信度估计.此外,给出了结构参数的无偏估计,并给出了模拟.结果表明,在考虑目标保费的情况下,当选取一个合适的权重,可以得到未来保费的最优估计.     

On Koul's minimum distance estimators in the regression models with long memory moving averages

This paper discusses the asymptotic behavior of Koul's minimum distance estimators of the regression parameter vector in linear regression models with long memory moving average errors, when the design variables are known constants. It is observed that all these estimators are asymptotically equivalent to the least-squares estimator in the first order.     

论双系统估计量的无偏性

人口普查质量评估中所使用的双系统估计量是否为无偏估计量是一个很值得深入讨论的问题。只有无偏,才能确保使用双系统估计量估计的目标总体实际人数及人口普查净误差平均等于它们的实际数。针对人口普查质量评估工作中所使用的双系统估计量,论证这个估计量的无偏性条件。采用从既定假设出发进行推演的路径论证。研究结果表明,双系统估计量是目标总体实际人数无偏估计量的必要但非充分的条件是,人口普查与其质量评估调查相互独立以及目标总体中的每一个人在人口普查中的登记概率相同,在质量评估调查中登记的概率也相同。     

A family of estimators for multivariate kurtosis in a nonnormal linear regression model

In this paper, we propose a new estimator for a kurtosis in a multivariate nonnormal linear regression model. Usually, an estimator is constructed from an arithmetic mean of the second power of the squared sample Mahalanobis distances between observations and their estimated values. The estimator gives an underestimation and has a large bias, even if the sample size is not small. We replace this squared distance with a transformed squared norm of the Studentized residual using a monotonic increasing function. Our proposed estimator is defined by an arithmetic mean of the second power of these squared transformed squared norms with a correction term and a tuning parameter. The correction term adjusts our estimator to an unbiased estimator under normality, and the tuning parameter controls the sizes of the squared norms of the residuals. The family of our estimators includes estimators based on ordinary least squares and predicted residuals. We verify that the bias of our new estimator is smaller than usual by constructing numerical experiments.     

F值函数的微分及其在FNN中的应用

本文引进了集值函数的ｓ－可微和模糊值（Ｆ值）函数的Ｆｓ－可微概念。给出了这两种可微性的几个判别条件。最后研究并得到了一类模糊神经网络（ＦＮＮ）的Ｆｓ－可微性和连续性。     

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.     

Minimum Distance Estimation in AR(1)-processes

In this paper a new minimum distance estimator is defined in case that the residuals of an AR(1)-process are contaminated normally distributed. This estimator is asymtotically normally distributed and in most cases less biased than the least square estimator. Furthermore, a method is presented to numerically calculate the minimum distance estimator as a root of an implicit function.     

Asymptotic Normality of the Whittle Estimator in Linear Regression Models with Long Memory Errors

This paper establishes the asymptotic normality of the Whittle estimator of the unknown dependence parameters in a linear regression model with long memory moving average errors. The design variables are taken to be deterministic or random. In the latter case they are assumed to have a moving average representation that includes both short and long memory. In all cases, it is observed that the rate of consistency of the regression parameter estimator has an effect on the asymptotic normality of the Whittle estimator.     

Estimating the Innovation Distribution in Nonlinear Autoregressive Models

The usual estimator for the expectation of a function under the innovation distribution of a nonlinear autoregressive model is the empirical estimator based on estimated innovations. It can be improved by exploiting that the innovation distribution has mean zero. We show that the resulting estimator is efficient if the innovations are estimated with an efficient estimator for the autoregression parameter. Efficiency of this estimator is necessary except when the expectation of the function can be estimated adaptively. Analogous results hold for heteroscedastic models.     

模糊ART神经网络在运动目标识别中的应用

本文在讨论模糊ＡＲＴ神经网络及其算法的基础上，研究和提出了一种三维运动目标识别方法，利用模糊ＡＲＴ神经网络对运动目标的目标侧面图形进行学习和模式识别。模拟实验表明了该方法的有效性。     

Convergence rates in density estimation for data from infinite-order moving average processes

Summary The effect of long-range dependence in nonparametric probability density estimation is investigated under the assumption that the observed data are a sample from a stationary, infinite-order moving average process. It is shown that to first order, the mean integrated squared error (MISE) of a kernel estimator for moving average data may be expanded as the sum of MISE of the kernel estimator for a same-sizerandom sample, plus a term proportional to the variance of the moving average sample mean. The latter term does not depend on bandwidth, and so imposes a ceiling on the convergence rate of a kernel estimator regardless of how bandwidth is chosen. This ceiling can be quite significant in the case of long-range dependence. We show thatall density estimators have the convergence rate ceiling possessed by kernel estimators.The research of Dr. Hart was done while he was visiting the Australian National University, and was supported in part by ONR Contract N00014-85-K-0723     

基于Pena距离的加权最小二乘估计的影响分析

利用Pena距离对加权线性最小二乘估计的影响问题进行讨论,得到加权最小二乘估计的Pena距离的表达式,对其性质进行讨论,从而得到高杠异常点的判别方法.文中对Pena距离与Cook距离的性能进行了对比,得到在一定条件下Pena距离优于Cook距离的结论.并通过数值实验对此方法的有效性进行验证.     

Weighted least absolute deviations estimation for periodic ARMA models

This paper investigates the weighted least absolute deviations estimator (WLADE) for causal and invertible periodic autoregressive moving average (PARMA) models. Asymptotic normality of the estimator is derived under a fractional moment condition. A simulation study is given to assess the performance of the proposed WLADE.     

Mixture decomposition via the simulated annealing algorithm

This paper presents the problem of the evaluation of the maximum likelihood estimator, when the likelihood function has multiple maxima, using the stochastic algorithm called ‘simulated annealing’. Analysis of the particular case of the decomposition of a mixture of five univariate normal distributions shows the properties of this methodology with respect to the E—M algorithm. The results are compared considering some distance measures between the estimated distribution functions and the true one.     

Estimating Functions for Nonlinear Time Series Models

This paper discusses the problem of estimation for two classes of nonlinear models, namely random coefficient autoregressive (RCA) and autoregressive conditional heteroskedasticity (ARCH) models. For the RCA model, first assuming that the nuisance parameters are known we construct an estimator for parameters of interest based on Godambe's asymptotically optimal estimating function. Then, using the conditional least squares (CLS) estimator given by Tjøstheim (1986, Stochastic Process. Appl., 21, 251–273) and classical moment estimators for the nuisance parameters, we propose an estimated version of this estimator. These results are extended to the case of vector parameter. Next, we turn to discuss the problem of estimating the ARCH model with unknown parameter vector. We construct an estimator for parameters of interest based on Godambe's optimal estimator allowing that a part of the estimator depends on unknown parameters. Then, substituting the CLS estimators for the unknown parameters, the estimated version is proposed. Comparisons between the CLS and estimated optimal estimator of the RCA model and between the CLS and estimated version of the ARCH model are given via simulation studies.     

Optimal Control of a Ship for Collision Avoidance Maneuvers

We consider a ship subject to kinematic, dynamic, and moment equations and steered via rudder under the assumptions that the rudder angle and rudder angle time rate are subject to upper and lower bounds. We formulate and solve four Chebyshev problems of optimal control, the optimization criterion being the maximization with respect to the state and control history of the minimum value with respect to time of the distance between two identical ships, one maneuvering and one moving in a predetermined way.Problems P1 and P2 deal with collision avoidance maneuvers without cooperation, while Problems P3 and P4 deal with collision avoidance maneuvers with cooperation. In Problems P1 and P3, the maneuvering ship must reach the final point with a given lateral distance, zero yaw angle, and zero yaw angle time rate. In Problems P2 and P4, the additional requirement of quasi-steady state is imposed at the final point.The above Chebyshev problems, transformed into Bolza problems via suitable transformations, are solved via the sequential gradient-restoration algorithm in conjunction with a new singularity avoiding transformation which accounts automatically for the bounds on rudder angle and rudder angle time rate.The optimal control histories involve multiple subarcs along which either the rudder angle is kept at one of the extreme positions or the rudder angle time rate is held at one of the extreme values. In problems where quasi-steady state is imposed at the final point, there is a higher number of subarcs than in problems where quasi-steady state is not imposed; the higher number of subarcs is due to the additional requirement that the lateral velocity and rudder angle vanish at the final point.     

Two step estimators of the minimum distance type for parameters of the ARMA(1,1) model

New minimum distance estimators are constructed with the help of a preliminary estimator. The asymptotic normality of the constructed estimator is proved with use of a uniform linear expansion of a randomly weighted residual empirical process in a non-standard neighborhood of the true parameter value. Also the question on asymptotic efficiency of the constructed estimator is discussed.