参数线性规划问题的新型光滑精确罚函数神经网络

针对不等式约束条件下,目标函数和约束条件中含有参数的线性规划问题,提出一种基于新型光滑精确罚函数的神经网络计算方法．引入误差函数构造单位阶跃函数的近似函数,给出一种更加精确地逼近于Ll精确罚函数的光滑罚函数,讨论了其基本性质;利用所提光滑精确罚函数建立了求解参数线性规划问题的神经网络模型,证明了该网络模型的稳定性和收敛性,并给出了详细的算法步骤．数值仿真验证了所提方法具有罚因子取值小、结构简单、计算精度高等优点．     

关于神经网络的能量函数

能量函数在神经网络的研究中有着非常重要的作用,人们普遍认为：只要能量函数沿着网络的解是下降的,能量函数的导数为零的点是网络的平衡态,能量函数有下界,则网络是稳定的且网络的平衡态是能量函数的极小点,文中取反例说明上述条件下不能保证网络的稳定性,并取例说明即使网络稳定也不能保证网络的平衡态与能量函数的极小点,证明了在网络具有上述条件的能量函数的情况下网络稳定的充分必要条件是网络的解有界,讨论了网络的平     

时滞细胞神经网络的稳定性分析

研究具有时滞的细胞神经网络（ＤＣＮＮ）的稳定性问题，利用构造Ｌｙａｐｕｎｏｖ泛函，常数变易法及不等式分析技巧，给出了时滞细胞神经网络全局指数稳定性和全局渐近性稳定性的充分判据，这些条件可用于设计出全局稳定的网络，因而具有重要的理论意义和应用价值。     

非线性零和微分对策的事件触发自适应动态规划算法

针对一类非线性零和微分对策问题,本文提出了一种事件触发自适应动态规划(event-triggered adaptive dynamic programming,ET--ADP)算法在线求解其鞍点.首先,提出一个新的自适应事件触发条件.然后,利用一个输入为采样数据的神经网络(评价网络)近似最优值函数,并设计了新型的神经网络权值更新律使得值函数、控制策略及扰动策略仅在事件触发时刻同步更新.进一步地,利用Lyapunov稳定性理论证明了所提出的算法能够在线获得非线性零和微分对策的鞍点且不会引起Zeno行为.所提出的ET--ADP算法仅在事件触发条件满足时才更新值函数、控制策略和扰动策略,因而可有效减少计算量和降低网络负荷.最后,两个仿真例子验证了所提出的ET--ADP算法的有效性.     

基于函数正交基展开的过程神经网络学习算法

过程神经网络的输入和连接权均可为时变函数，过程神经元增加了一个对于时间的聚合算子，使网络同时具有时空二维信息处理能力．该文在考虑过程神经网络对时间聚合运算的复杂性的基础上，提出了一种基于函数正交基展开的学习算法．在网络输入函数空间中选择一组适当的函数正交基，将输入函数和网络权函数都表示为该组正交基的展开形式，利用基函数的正交性．简化过程神经元对时间的聚合运算．应用表明，算法简化了过程神经网络的计算复杂度，提高了网络学习效率和对实际问题求解的适应性．以旋转机械故障诊断问题和油藏开发过程采收率的模拟为例验证了算法的有效性．     

Ｓｔｅｗａｒｔ主动隔振平台的神经网络自适应控制

针对Ｓｔｅｗａｒｔ主动隔振平台,提出一种基于径向基函数（ＲＢＦ）神经网络的多输入多输出自适应隔振控制方法．考虑外界振动对Ｓｔｅｗａｒｔ主动隔振平台动态特性的影响,建立了隔振平台在工作空间中的动力学模型．推导出ＲＢＦ神经网络的权值矩阵、高斯基函数中心和宽度的在线自适应调节律,以使神经网络快速逼近系统的非线性动态函数．应用Ｌｙａｐｕｎｏｖ稳定性理论,证明了在扰动力和神经网络逼近误差有界的条件下,闭环控制系统滤波误差和ＲＢＦ神经网络各调节参数估计误差的一致最终有界．仿真结果表明,该控制方法能有效地抑制不同方向的低频有界振动.

     

时变采样周期网络控制系统的鲁棒容错控制器设计

研究具有时变采样周期网络控制系统的执行器失效的完整性问题．假设系统任意两个连续采样间隔具有上界,利用输入时延法,将时变采样周期网络控制系统等价转化为连续时变时延网络控制系统．在此基础上,基于时延条件,应用Ｌｙａｐｕｎｏｖ稳定性理论和线性矩阵不等式（ＬＭＩｓ）方法证明了鲁棒容错控制律的存在条件,设计了鲁棒容错控制器,并给出了系统完整性条件下的最大允许时延的估计方法．仿真结果验证了所提方法的可行性和有效性．     

基于精确罚函数的一类广义非线性神经网络模型

针对一般的非线性优化问题定义了一种2次非线性罚函数,证明了在一定条件下对 应的罚优化问题的精确罚定理,由此引进了一种广义非线性神经网络模型,并证明了这种网络 的平衡点与能量函数之间的联系,在一定条件下对应的平衡点收敛到原问题的最优解.这种神 经网络模型对于求解许多优化问题具有重要的作用.     

基于自适应RBF 网络补偿的智能车辆循迹控制

针对智能车辆这一复杂非线性时变系统的循迹控制问题,提出一种基于Lyapunov函数方法的RBF神经网络自适应补偿控制策略.首先建立了车辆循迹控制的动力学名义模型;然后利用RBF神经网络对车辆循迹控制名义模型的不精确部分进行自适应补偿;最后应用Lyapunov稳定性理论推导出RBF网络权值的训练规则并证明了控制系统的稳定性.仿真结果表明,该方法提高了循迹控制的精度,具有较高的可行性和实用性.     

一种稳定的机器人神经网络控制器研究

研究一种稳定的机器人神经网络（ＮＮ）控制器，提出了由神经网络控制器和监督控制器构成的控制方案，给出了控制器的设计方法及ＮＮ学习自适应律，并基于Ｌｙａｐｕｎｏｖ方法证明了控制系统的稳定性和ＮＮ参数收敛性，仿真结果表明该控制方案具有良好的鲁棒性和参数收敛性，从而证明控制器的有效性。     

Synthesis of fault-tolerant feedforward neural networks usingminimax optimization

In this paper we examine a technique by which fault tolerance can be embedded into a feedforward network leading to a network tolerant to the loss of a node and its associated weights. The fault tolerance problem for a feedforward network is formulated as a constrained minimax optimization problem. Two different methods are used to solve it. In the first method, the constrained minimax optimization problem is converted to a sequence of unconstrained least-squares optimization problems, whose solutions converge to the solution of the original minimax problem. An efficient gradient-based minimization technique, specially tailored for nonlinear least-squares optimization, is then applied to perform the unconstrained minimization at each step of the sequence. Several modifications are made to the basic algorithm to improve its speed of convergence. In the second method a different approach is used to convert the problem to a single unconstrained minimization problem whose solution very nearly equals that of the original minimax problem. Networks synthesized using these methods, though not always fault tolerant, exhibit an acceptable degree of partial fault tolerance.     

融合卷积神经网络与多层感知器的鞍部识别方法

针对传统鞍部识别方法中特征选择困难及未考虑鞍部与其它地形要素的共生关系等问题,利用深度卷积神经网络的特征自学习性能,提出了一种卷积神经网络与多层感知器相结合的混合模型实现DEM数据中的鞍部要素识别.首先设计改进的卷积神经网络模型自动提取鞍部的深度特征,经过Softmax分类器得到候选鞍部点,再运用多层感知器对候选鞍部点的位置进行精细回归,标识出最终的鞍部要素坐标.通过自建的鞍部样本集SADDLE-100训练网络模型,并在三种不同的山地样区进行实验,实验结果表明该方法比其它鞍部识别方法的漏提率减少约50%,正确识别率提高6.7%,在一定程度上避免了人工选择特征造成的鞍部语义信息缺失现象,为DEM中的点状要素识别提供了新的技术途径.     

基于免疫算法的网络功能异构冗余部署方法

针对现有安全防御手段无法抵御网络功能虚拟化平台中众多未知的漏洞与后门的问题。运用拟态防御思想,提出一种网络功能虚拟化的拟态防御架构,并针对其中的异构体池构建问题设计了一种基于免疫算法的网络功能异构冗余部署方法。首先,结合熵值法对异构体之间的异构度进行量化评估;然后,以实现异构体之间异构度最大为优化目标将网络功能异构冗余部署问题构建成极大极小问题;最后,基于免疫算法快速求解最优部署方案。仿真结果表明,该方法可以迅速收敛到最优部署方案,并保证异构体之间的异构度值整体分布在较高的水平,有效增加了异构体池的多样性,提升了攻击者的攻击难度。     

An Equitable Bandwidth Allocation Model for Video-on-Demand Networks

Video-on-Demand (VOD) or near-VOD services are expected to grow significantly over time, providing diverse programs for home entertainment, learning and training, news-on-demand, and other applications. These services require large bandwidth resources. We present a model for bandwidth allocation in a tree network with limited link capacities, where a server at the root node repeatedly broadcasts copies of various programs. The time intervals between successive broadcasts of each program can be increased at subsequent nodes, or the video quality can be decreased, thus providing different service performance to different nodes while satisfying the capacity constraints. The model is formulated as an equitable resource allocation problem with a lexicographic minimax objective function and tree-like ordering constraints. We present a lexicographic minimax algorithm that allocates each link’s bandwidth among the programs carried on the link. The algorithm repeatedly solves minimax problems, and fixes some variables at their optimal value after the solution of each such problem. The algorithm for solving the minimax problems uses a bisection search to find the minimax solution with the minimal decision variable values. The model also provides an ordered list of links from the most critical link to the least critical link, a useful feature for capacity expansion planning decisions.     

Noncausal minimax linear state estimation for systems with uncertain second-order statistics

This note considers the problem of minimax state estimation of the states of a linear time-invariant system which is driven by and observed in the presence of noise processes with uncertain second-order statistics. When the process noise and observations are scalars, the problem is shown to be equivalent to a scalar minimax estimation problem. The existence of a minimax solution is thereby established, and the minimax filter is shown to be a linear transformation of the minimax filter for the scalar problem.     

Layout of facilities with some fixed points

This paper deals with the location of facilities or “movable” points on a planar area, on which there already exist fixed points. The minimax criterion for optimality is used and distances among points are assumed to be rectilinear. Two very efficient algorithms for the solution of the problem are presented. One is based on a univariate search, and the other on a steepest descent method. Some computational results are presented.     

Wavelets and Estimation of Discontinuous Functions

The paper considers the problem of estimating a signal with finitely many points of discontinuity from observations against white Gaussian noise. It is shown that, with an appropriate choice of a generator polynomial, an estimation method based on wavelets yields asymptotically minimax (up to a constant) estimates for functions sufficiently smooth outside the discontinuity points.     

The Wonham filter under uncertainty: A game–theoretic approach

The paper is devoted to a state filtering problem of Markov jump processes given the continuous and/or counting observations. All the transition intensity matrix, observation plan and counting intensity are parameterized by a random vector with uncertain distribution on a known support set.The estimation problem is formulated in minimax settings with a conditional optimality criterion. We reduce the initial minimax problem to a dual problem of constrained quadratic optimization. The corresponding numerical algorithm of minimax filtering is presented as well as its illustrative implementation in the monitoring of a TCP link status under uncertainty.     

Design of minimax robust LQG controllers under parameter and noise uncertainties

The problem of design of minimax robust LQG controllers for linear systems with parameter and noise uncertainties is considered in this paper. Necessary and sufficient conditions for converting this problem to a two-person, zero-sum continuous game problem are presented. A simple procedure for design of a suboptimal minimax robust LQG controller, i.e., the LQG controller for least-favourable model, is proposed. Necessary and sufficient conditions for the existence of a saddle point are established. Under these conditions, the controller obtained is exactly the minimax LQG controller. When there does not exist a saddle point, the worst-case error between the controller obtained and the minimax robust LQG controllers under described uncertainties is bounded.     

基于改进Hopfield神经网络的图像特征点匹配算法

针对图像特征点匹配算法的运行时间呈指数增长的问题,提出了一种新的匹配算法NHop.该算法通过加入新的网络输入输出函数、点对间差异的度量和启发式选择目标点的方式,对传统的Hopfield神经网络进行了改进.新算法不仅解决了传统Hopfield神经网络运行时间长、能量函数易陷入局部极小点的问题,而且也有效地实现了图像特征点的匹配.实验结果表明,与传统的Hopfield神经网络相比,NHop算法的匹配速度更快、准确率更高,对于图像特征点的匹配效果更好.