光滑拉格朗日神经网络解决非光滑最优化问题

针对目标函数是局部Lipschitz函数,其可行域由一组等式约束光滑凸函数组成的非光滑最优化问题,通过引进光滑逼近技术将目标函数由非光滑函数转换成相应的光滑函数,进而构造一类基于拉格朗日乘子理论的神经网络,以寻找满足约束条件的最优解。证明了神经网络的平衡点集合是原始非光滑最优化问题关键点集合的一个子集;当原始问题的目标函数是凸函数时,最小点集合与神经网络的平衡点集合是一致的。通过仿真实验验证了理论结果的正确性。     

一种新型拉格朗日神经网络解决非光滑优化问题

针对函数是非光滑的问题以及采用固定惩罚项的弊端,利用 Clarke广义梯度的理论和lagrange乘子法的思想,建立了一个微分包含的神经网络模型。此模型是采用罚函数的方法,有效避免了固定项的缺陷。理论证明了网络是有全局解的,并且收敛到原问题的关键点集,对于凸问题来说网络收敛的平衡点就是问题的最优点。最后通过仿真实验验证了理论结果的正确性。     

递归神经网络方法解决非光滑伪凸优化问题

针对目标函数为非光滑伪凸函数且带有等式约束和不等式约束的优化问题,基于罚函数以及微分包含的思想,构建一个层次仅为一层且不包含惩罚算子的新型递归神经网络模型。该模型不用提前计算惩罚参数,能够很好地收敛。理论证明全局解存在,模型的状态解能够在有限的时间内进到原目标函数的可行域并不再离开,其状态解最终收敛到目标函数的一个最优解。仿真实验证实了理论结果的可行性。     

光滑神经网络解决一类线性约束的非Lipschitz优化问题

带有线性不等式约束的非光滑非优化问题被广泛应用于稀疏优化,具有重要的研究价值.为了解决这类问题,提出了一种基于光滑化和微分包含理论的神经网络模型.通过理论分析,证明了所提神经网络的状态解全局存在,轨迹能够在有限时间进入可行域并永驻其中,且任何聚点都是目标优化问题的广义稳定点.最后给出数值实验和图像复原实验验证神经网络在理论和应用中的有效性.与现有神经网络相比,它具有以下优势：初始点可以任意选取;避免计算精确罚因子;无需求解复杂的投影算子.     

一类非光滑非凸优化问题的神经网络方法

提出了解决一类带等式与不等式约束的非光滑非凸优化问题的神经网络模型。证明了当目标函数有下界时,神经网络的解轨迹在有限时间收敛到可行域。同时,神经网络的平衡点集与优化问题的关键点集一致,且神经网络最终收敛于优化问题的关键点集。与传统基于罚函数的神经网络模型不同,提出的模型无须计算罚因子。最后,通过仿真实验验证了所提出模型的有效性。     

一种解决非光滑伪凸优化问题的新型神经网络

针对带有不等式约束条件的非光滑伪凸优化问题，提出了一种基于微分包含理论的新型递归神经网络模型，根据目标函数与约束条件设计出随着状态向量变化而变化的罚函数，使得神经网络的状态向量始终朝着可行域方向运动，确保神经网络状态向量可在有限时间内进入可行域，最终收敛到原始优化问题的最优解。最后，用两个仿真实验用来验证神经网络的有效性与准确性。与现有神经网络相比，它是一种新型的神经网络模型，模型结构简单，无需计算精确的罚因子，最重要的是无需可行域有界。     

一类非光滑优化及其在控制系统稳定化中的应用

研究一类来自控制系统稳定化中的非光滑优化问题．考虑Lyapunov函数是非光滑的,特别是有限个光滑函数的极大值函数．建立了相应的非光滑优化模型,进一步导出了这类非光滑优化的KKT系统,然后基于非线性互补函数将KKT系统转化成一个非光滑方程组,最后分别用广义牛顿法和光滑化牛顿法求解此非光滑方程组。使得此类稳定化设计可以具体实现．     

非光滑非线性系统的非光滑连续控制

针对具有非光滑非线性的系统,提出了一种非光滑连续控制方法,通过非光滑建模方法能够快速精确地补偿系统中有害的非光滑非线性,同时通过非光滑连续控制引入一些有益的非光滑非线性以获得快速高精度的控制性能,给出了实验迟滞曲线和建模结果。讨论了该项技术在非光滑非线性控制系统中的应用前景。     

非单调信赖域方法求解无约束非光滑优化问题

提出了非单调信赖域算法求解无约束非光滑优化问题,并和经典的信赖域方法作比较分析。同时,设定了一些条件,在这些假设条件下证明了该算法是整体收敛的。数值实验结果表明,非单调策略对无约束非光滑优化问题的求解是行之有效的,拓展了非单调信赖域算法的应用领域。     

Solving fuzzy shortest path problems by neural networks

In this paper, we introduce the neural networks for solving fuzzy shortest path problems. The penalization of the neural networks is realized after transforming into crisp shortest path model. The procedure and efficiency of this approach are shown with numerical simulations.     

Predicting the Brazilian stock market through neural networks and adaptive exponential smoothing methods

The study of financial markets has been addressed in many works during the last years. Different methods have been used in order to capture the non-linear behavior which is characteristic of these complex systems. The development of profitable strategies has been associated with the predictive character of the market movement, and special attention has been devoted to forecast the trends of financial markets. This work performs a predictive study of the principal index of the Brazilian stock market through artificial neural networks and the adaptive exponential smoothing method, respectively. The objective is to compare the forecasting performance of both methods on this market index, and in particular, to evaluate the accuracy of both methods to predict the sign of the market returns. Also the influence on the results of some parameters associated to both methods is studied. Our results show that both methods produce similar results regarding the prediction of the index returns. On the contrary, the neural networks outperform the adaptive exponential smoothing method in the forecasting of the market movement, with relative hit rates similar to the ones found in other developed markets.     

Subgradient-based feedback neural networks for non-differentiable convex optimization problems

1 Introduction Optimization problems arise in a broad variety of scientific and engineering applica- tions. For many practice engineering applications problems, the real-time solutions of optimization problems are mostly required. One possible and very pr…     

Generalized gradient projection neural networks for nonsmooth optimization problems

Generalized gradient projection neural network models are proposed to solve nonsmooth convex and nonconvex nonlinear programming problems over a closed convex subset of R n . By using Clarke’s generalized gradient, the neural network modeled by a differential inclusion is developed, and its dynamical behavior and optimization capabilities both for convex and nonconvex problems are rigorously analyzed in the framework of nonsmooth analysis and the differential inclusion theory. First for nonconvex optimizati...     

Solving fully fuzzy polynomials using feed-back neural networks

Recently, there has been a considerable amount of interest and practice in solving many problems of several applied fields by fuzzy polynomials. In this paper, we have designed an artificial fuzzified feed-back neural network. With this design, we are able to find a solution of fully fuzzy polynomial with degree n. This neural network can get a fuzzy vector as an input, and calculates its corresponding fuzzy output. It is clear that the input–output relation for each unit of fuzzy neural network is defined by the extension principle of Zadeh. In this work, a cost function is also defined for the level sets of fuzzy output and fuzzy target. Next a learning algorithm based on the gradient descent method will be defined that can adjust the fuzzy connection weights. Finally, our approach is illustrated by computer simulations on numerical examples. It is worthwhile to mention that application of this method in fluid mechanics has been shown by an example.     

Derivative and GA-based methods in metamodeling of back-propagation neural networks for constrained approximate optimization

Artificial neural networks (ANN) have been extensively used as global approximation tools in the context of approximate optimization. ANN traditionally minimizes the absolute difference between target outputs and approximate outputs thereby resulting in approximate optimal solutions being sometimes actually infeasible when it is used as a metamodel for inequality constraint functions. The paper explores the development of the efficient back-propagation neural network (BPN)-based metamodel that ensures the constraint feasibility of approximate optimal solution. The BPN architecture is optimized via two approaches of both derivative-based method and genetic algorithm (GA) to determine interconnection weights between layers in the network. The verification of the proposed approach is examined by adopting a standard ten-bar truss problem. Finally, a GA-based approximate optimization of suspension with an optical flying head is conducted to enhance the shock resistance capability in addition to dynamic characteristics.     

Calibrating artificial neural networks by global optimization

Artificial neural networks (ANNs) are used extensively to model unknown or unspecified functional relationships between the input and output of a “black box” system. In order to apply the generic ANN concept to actual system model fitting problems, a key requirement is the training of the chosen (postulated) ANN structure. Such training serves to select the ANN parameters in order to minimize the discrepancy between modeled system output and the training set of observations. We consider the parameterization of ANNs as a potentially multi-modal optimization problem, and then introduce a corresponding global optimization (GO) framework. The practical viability of the GO based ANN training approach is illustrated by finding close numerical approximations of one-dimensional, yet visibly challenging functions. For this purpose, we have implemented a flexible ANN framework and an easily expandable set of test functions in the technical computing system Mathematica. The MathOptimizer Professional global-local optimization software has been used to solve the induced (multi-dimensional) ANN calibration problems.     

Solving TSP by using Lotka–Volterra neural networks

This paper proposes a new approach to solve traveling salesman problem (TSP) by using a class of Lotka–Volterra neural networks (LVNN) with global inhibition. Some stability criteria that ensure the convergence of valid solutions are obtained. It is proved that an equilibrium state is stable if and only if it corresponds to a valid solution of the TSP. Thus, a valid solution can always be obtained whenever the network convergence to a stable state. A set of analytical conditions for optimal settings of LVNN is derived. Simulation results illustrate the theoretical analysis.