求解复杂优化问题的基于信息熵的自适应蚁群算法

针对基本蚁群算法存在收敛速度慢、易陷入局部最优、计算复杂且不易求解连续优化问题等缺陷 ,提出了一种基于信息熵的改进自适应蚁群算法 ,采用由信息熵控制的路径选择及随机扰动策略实现了算法的自适应调节 ,克服了基本蚁群算法的不足 .典型的 NP-hard问题的计算实例表明 ,该方法具有较好的收敛性、稳定性和鲁棒性 ,可用于离散及连续的组合优化问题求解中 ,其不失为求解复杂组合优化问题的一种较好的方法 .     

基于GA-SVM的水资源可持续利用评价

把水资源可持续利用评价问题看成是一个分类问题,利用支持向量机良好的鲁棒性和分类精确性进行评价,并用遗传算法优化了SVM的参数,使其分类精确度更高.对黑龙江省十三个地区进行了实例应用,与人工神经网络和GD-IIM法的结果进行了比较,结果表明,支持向量机模型简单、通用、精度高,可在水资源可持续利用实际评价中推广应用.     

二阶非线性系统概周期解的存在性

该文研究某些二阶非线性系统, 利用平均法给出了非线性系统概周期解存在性的某些充分条件, 推广了已知结果. 二个特殊系统用于说明其结果的可行性和更一般性.     

遗传算子的改进

遗传算法是受自然选择和自然遗传启发的数值优化算法.它没有任何本身所固有的限制,直接时群体进行操作,自动获取知识用于指导优化和调整搜索方向,保持物种的多样性.其进化思想是解决复杂难题的一个范例,它是一种可在相当宽广领域应用的普遍算法.从理论上分析它的遗传操作算子还存在着某些不足,怎样设计高效的遗传操作算子是解决难题的关键,本文讨论有关遗传操作算子的一些改进.     

基于t分布的自适应花授粉算法

花授粉算法是一种新型启发式优化算法,算法存在易陷入局部最优、后期收敛速度慢等缺陷,为了进一步提高花授粉算法的寻优性能,在异花授粉过程中引入t分布变异算子,提出了一种基于t分布的自适应花授粉算法(tFPA).通过7个标准测试函数进行测试比较,并对改进算法的时间复杂度进行分析,仿真结果表明,改进算法是可行有效的,其寻优速度、寻优精度以及鲁棒性均有很大程度的改善.     

广义二分搜索及其在 LP 多项式算法复杂度证明中的应用

Khachiyan 和 Karmarkar 方法的提出,不仅解决了长期悬而未决的线性规划(LP)问题的多项式时间算法的存在性问题,而且开辟了优化算法设计上新的方法论体系.目前的兴趣之一是把这一方法论体系应用到一般的连续优化问题中去.一个组合优化问题,同一般优化问题一样,可以表达成一个二元组((?),c),其中(?)是可行解集合,c 是定义在(?)上的实目标函数.对于组合问题,一般地,(?)是离     

基于卷积神经网络模型数值求解双曲型偏微分方程的研究

人工神经网络近年来得到了快速发展,将此方法应用于数值求解偏微分方程是学者们关注的热点问题.相比于传统方法其具有应用范围广泛（即同一种模型可用于求解多种类型方程）、网格剖分条件要求低等优势,并且能够利用训练好的模型直接计算区域中任意点的数值.该文基于卷积神经网络模型,对传统有限体积法格式中的权重系数进行优化,以得到在粗粒度网格下具有较高精度的新数值格式,从而更适用于复杂问题的求解.该网络模型可以准确、有效地求解Burgers方程和level set方程,数值结果稳定,且具有较高数值精度.     

基于统计引导和多项式差分学习的樽海鞘优化算法

樽海鞘优化算法相较于传统的群体智能优化算法,具有较好的鲁棒性和寻优能力。但仍存在全局寻优能力有限、执行效率不够高、易陷入局部极值的缺陷。针对上述问题,本文提出一种新的多项式差分学习策略,以区分和改进传统的线性差分方法;并设计一种随机种群划分方式,使得信息可以在邻域拓扑内均匀传递;另外,本文定义多项式差分学习的全局探索算子和局部开发算子,引入统计引导系数A,开启不同的多项式学习方法,从而进一步提高算法的全局搜索能力和寻优精度。最后,本文通过标准测试函数和实际应用问题的对比检验,证实了改进算法的优越性和鲁棒性,拓展和丰富了原算法的应用范围。     

混沌粒子群神经网络在上证指数预测中的应用

上证指数预测是一个非常复杂的非线性问题,为了提高对上证指数预测的准确性,本文采用基于混沌粒子群(CPSO)算法对BP神经网络算法改进的方法来进行预测.BP神经网络算法目前已经应用到预测、聚类、分类等许多领域,取得了不少的成果.但自身也有明显的缺点,比如易陷入局部极小值、收敛速度慢等.用混沌粒子群算法改进BP神经网络算法的基本思想是用混沌粒子群算法优化BP神经网络算法的权值和阈值,在粒子群算法中加入混沌元素,提高粒子群算法的全局搜索能力.对上证指数预测的结果表明改进后的预测方法,具有更好的准确性.     

基于多目标进化聚类的信用风险特征识别

在信用风险识别领域,聚类算法常被用于区分不同风险等级的样本并识别风险特征。然而该领域中通常面临高维数据处理问题,导致传统聚类算法存在不适应此类问题的缺陷:易陷入局部最优、受冗余特征干扰、鲁棒性不强等。采用高维信用风险数据,研究上市公司信用风险,建立信用风险特征识别的三目标优化模型,设计基于分解的多目标子空间聚类算法进行求解。通过算法的横向对比实验,展示了所提出的算法在聚类精度和鲁棒性方面的优势,并根据聚类算法的权重分配结果,归纳总结上市公司信用风险评估过程中应重点关注的指标。     

基于粒子群的模糊神经网络的短时交通流量组合预测

为了进一步提高短时交通流量预测的精度,提出了一种粒子群算法的模糊神经网络组合预测模型,模糊神经网络融合了神经网络的学习机制和模糊系统的语言推理能力等优点,弥补各自不足,将自回归求和滑动平均(ARIMA)和灰色Verhulst模型进行初步预测,并将两种初步预测的结果作为模糊神经网络的输入,构建基于改进模神经网络的组合预测模型,在此基础上进行训练和预测,其中模糊神经网络的相关参数由改进粒子群来优化,利用本方法来对南京市汉中路短时交通流量进行预测,结论表明:方法充分发挥了单一模型的优势,比单一的预测模型更加精确,是短时交通流量预测的一个有效方法。     

我国上市公司被特别处理的组合预测模型研究

针对组合预测比单项预测具有更高的预测精度，本提出了一种基于模糊神经网络的上市公司被ST的非线性组合建模与预测新方法，并给出了相应的混合学习算法。通过与多元线性回归模型、Fisher模型和Logistc回归模型的预测结果对比表明，该方法具有预测精度高，学习与泛化能力强，适应性广的优点。     

Neural networks and seasonality: Some technical considerations

Debate continues regarding the capacity of feedforward neural networks (NNs) to deal with seasonality without pre-processing. The purpose of this paper is to provide, with examples, some theoretical perspective for the debate. In the first instance it considers possible specification errors arising through use of autoregressive forms. Secondly, it examines seasonal variation in the context of the so-called ‘universal approximation’ capabilities of NNs, finding that a short (bounded) sinusoidal series is easy for the network but that a series with many turning points becomes progressively more difficult. This follows from results contained in one of the seminal papers on NN approximation. It is confirmed in examples which also show that, to model seasonality with NNs, very large numbers of hidden nodes may be required.     

粒子群优化模糊神经网络在语音识别中的应用

针对模糊神经网络训练采用BP算法比较依赖于网络的初始条件,训练时间较长,容易陷入局部极值的缺点,利用粒子群优化算法(PSO)的全局搜索性能,将PSO用于模糊神经网络的训练过程.由于基本PSO算法存在一定的早熟收敛问题,引入一种自适应动态改变惯性因子的PSO算法,使算法具有较强的全局搜索能力.将此算法训练的模糊神经网络应用于语音识别中,结果表明,与BP算法相比,粒子群优化的模糊神经网络具有较高的收敛速度和识别率.     

A novel chaotic search for quadratic assignment problems

We propose a novel method for solving the quadratic assignment problems. First, we realize the conventional tabu search on a neural network, and modify it to a chaotic version. Our novel method includes both effects of chaotic dynamics and tabu search. We compare the performance of the novel chaotic search with the conventional tabu search and an exponential tabu search whose memory effect for tabu (forbidding previous moves) decays exponentially. We show that the exponential tabu search has higher performance than the conventional tabu search, and further that the novel method with a chaotic neural network exhibits the best performance. We also propose a controlling method of the chaotic neural network for realizing easy and robust applications of our method. Then, better performance can be realized without manual parameter setting for various problems.     

ESL-SELO: A robust image denoising algorithm with penalty

Robust image recovery methods have been attracted more and more attention in recent decades for its good property of tolerating system errors or measuring noise. In this paper, we propose a new robust method (ESL-SELO) to recover nosing image, which combine exponential loss function and seamless-L0 (SELO) penalty function to guarantee both accuracy and robustness of the estimator. Theoretical result showed that our method has a local optimal solution and good asymptotic properties. Finally, we compare our method with other methods in simulation which shows better robustness and takes much less time.     

Improving Prediction of Neural Networks: A Study of Two Financial Prediction Tasks

Neural networks are excellent mapping tools for complex financial data. Their mapping capabilities however do not always result in good generalizability for financial prediction models. Increasing the number of nodes and hidden layers in a neural network model produces better mapping of the data since the number of parameters available to the model increases. This is detrimental to generalizability of the model since the model memorizes idiosyncratic patterns in the data. A neural network model can be expected to be more generalizable if the model architecture is made less complex by using fewer input nodes. In this study we simplify the neural network by eliminating input nodes that have the least contribution to the prediction of a desired outcome. We also provide a theoretical relationship of the sensitivity of output variables to the input variables under certain conditions. This research initiates an effort in identifying methods that would improve the generalizability of neural networks in financial prediction tasks by using mergers and bankruptcy models. The result indicates that incorporating more variables that appear relevant in a model does not necessarily improve prediction performance.     

Robust exponential stability of discrete‐time uncertain impulsive neural networks with time‐varying delay

The purpose of this paper is to investigate the robust exponential stability of discrete‐time uncertain impulsive neural networks with time‐varying delay. By using Lyapunov functions together with Razumikhin technique, some new robust exponential stability criteria are presented. The obtained results show that the robust stability can be retained under certain impulsive perturbations for the neural network, which has the robust stability property. The obtained results also show that impulses can robustly stabilize the neural network, which does not have the robust stability property. Some examples, together with their simulations, are also given to show the effectiveness and the advantage of the presented results. It should be noted that the impulsive robust exponential stabilization result for discrete‐time neural network with time‐varying delay is given for the first time. Copyright © 2012 John Wiley & Sons, Ltd.     

Representing and Learning Distributions with the Aid of a Neural Network

This paper describes a method by which a neural network learns to fit a distribution to sample data. The neural network may be used to replace the input distributions required in a simulation or mathematical model and it allows random variates to be generated for subsequent use in the model. Results are given for several data sets which indicate the method is robust and can represent different families of continuous distributions. The neural network is a three-layer feed-forward network of size (1-3-3-1). This paper suggests that the method is an alternative approach to the problem of selection of suitable continuous distributions and random variate generation techniques for use in simulation and mathematical models.     

Artificial neural networks in bankruptcy prediction: General framework and cross-validation analysis

In this paper, we present a general framework for understanding the role of artificial neural networks (ANNs) in bankruptcy prediction. We give a comprehensive review of neural network applications in this area and illustrate the link between neural networks and traditional Bayesian classification theory. The method of cross-validation is used to examine the between-sample variation of neural networks for bankruptcy prediction. Based on a matched sample of 220 firms, our findings indicate that neural networks are significantly better than logistic regression models in prediction as well as classification rate estimation. In addition, neural networks are robust to sampling variations in overall classification performance.