一种结构自适应的径向基函数神经网络

提出了一种新的结构自适应的径向基函数(RBF)神经网络模型。在该模型中,自组织映射(SOM)神经网络作为聚类网络,采用无监督学习算法对输入样本进行自组织分类,并将分类中心及其对应的权值向量传递给RBF神经网络,分别作为径向基函数的中心和相应的权值向量;RBF神经网络作为基础网络,采用高斯函数实现输入层到隐层的非线性映射,输出层则采用有监督学习算法训练网络的权值,从而实现输入层到输出层的非线性映射。通过对字母数据集进行仿真,表明该网络具有较好的性能。     

径向基概率神经网络的一种自组织学习算法

介绍了径向基概率神经网络 (RBPNN)的一种自组织学习算法 ,该算法把径向基概率神经网络的结构原理与自组织聚类算法相结合 ,不仅能够完成对训练样本的聚类分析 ,标识出训练样本的类别属性 ,而且能够自动完成基于该训练样本集的径向基概率神经网络的训练过程 .本算法用于对 IRIS三种花型识别在训练阶段达到 97.33%的识别效果 ,而在推广能力方面 ,由本文算法得到的 RBPNN优于有标识的训练样本的 RBFNN     

机械臂系统自组织模糊径向基神经网络控制器设计

以模型为基础的传统的控制理论在设计控制器时需要预先知道被控对象的数学模型,而机械臂具有非线性、不确定的动态特性,因此应用传统的控制理论难以设计出适当的控制器.为解决此问题,本文应用自组织模糊径向基神经网络算法对机械臂的控制器进行设计,将径向基神经网络应用于自组织模糊控制算法,以及时调整学习率和权重分配,改善系统控制性能...     

径向基神经网络的一种自适应混合学习算法

为设计具有良好逼近性能的径向基神经网络,提出一种两层结构的自适应混合学习算法.内层迭代过程综合了梯度下降法和智能优化方法的优点,采用基于衰减梯度信息的智能优化方法,对具有固定结构的网络进行参数训练;外层迭代根据内层迭代的效果,利用最优停止规则自适应地动态调节网络隐含层节点数,使算法以较大概率收敛至全局最优.设计了网络结构修正算子,实现对最终结果的进一步简化.最后,文章给出算法实现的具体步骤,并通过仿真实例验证了算法有效性和可行性.     

基于混沌映射的非径向对称基函数的神经网络模型

为提高神经网络模型的预测精度,构建了非径向对称基函数神经网络模型结构。为确定非径向对称基函数神经网络模型参数,采用Ulam-von Neumann映射规则确定混沌变量,利用混沌变量的遍历性获得不同网络结构参数下的最优网络输出,以减少所构建网络模型的实际输出与期望输出的差值,并利用模型输出的误差变化率以决定是否增加新的隐层节点。给出基于混沌映射的非径向对称基函数的网络模型构建步骤。采用基于Mackey-Glass时滞微分方程的混沌时间序列预测问题验证该模型的预测精度,并同其他文献对该序列预测的精度以及所需隐层节点数作对比。比较结果表明,采用该设计模型具有对时间序列预测精度高且所需网络结构规模小等优点。     

一种径向基函数神经网络生成模糊系统的方法研究

如何建立合适的模糊规则.是模糊系统设计的关键和难点。传统的方法是依靠统计分析或经验建立模糊规则库[lJ,不仅难度大,而且建立的模糊系统缺乏适应能力。人工神经网络(ANN)技术的发展为模糊规则的自动获取提供了一条新途径.许多学者研究ANN与模糊系统的融合问题,其主要目的就是利用ANN的学习能力和自适应能力,从样本中提取模糊规则.形成具有自适应能力的模糊系统。尽管利用多层前馈网获取模糊规则口     

一种径向基函数神经网络的参数求解方法

为了求解径向基函数神经网络的权值,首先分析了传统基于训练误差的方法,发现该方法容易造成数据过拟合,原因在于训练误差是风险函数的下偏估计;因此,文中提出采用缺一交叉验证得分代替训练误差,来实现无偏估计风险函数;实验对摩托数据与玻璃数据进行拟合,证实了基于缺一交叉验证的方法优于传统基于训练误差的方法,且所得到的径向基函数网络能够较光滑地拟合数据,不会造成过拟合.     

一种基于Gaussian函数的双向选择径向基函数神经网络算法

径向基函数神经网络是一类重要的神经网络算法。本文对现有的径向基函数神经网络算法进行了总结分析,将现有算法分为前向选择和后向选择两类。在分析各自优缺点的基础上从提高神经网络泛化能力的角度提出了一种新的基于Gaussian函数的双向选择径向基函数神经网络算法——BSRBF,从数理角度研究了神经元选择的基本技术方法,并对算法的基本思想和具体步骤进行了阐述。最后,用一个实验对比验证了双向选择算法的有效性。     

一种权值直接确定及结构自适应的Chebyshev基函数神经网络

基于函数逼近理论,构造一种Chebyshev基函数神经网络模型.推导出该网络模型的权值直接确定方法,可一步计算出权值,克服了传统BP神经网络学习率选取困难、学习过程冗长和易陷入局部极小等缺点.在此基础上,设计了基于二分搜索的结构自适应算法,根据精度要求自动确定网络最优结构.理论分析及仿真验证均表明,该网络不仅能够快速地完成网络权值确定和结构自适应,且具有优异的学习与逼近能力,而且对随机加性噪声也具有较好的抑制作用.     

基于自适应粒子群优化径向基函数神经网络的语音转换

语音转换是指在保持源说话人语义内容不变的前提下,通过改变源说话人的个性特征,使其听起来像目标说话人的语音。本文提出一种自适应粒子群优化算法训练径向基函数神经网络进行语音特征建模,以获取说话人谱包络的映射关系;此外,考虑到说话人谱包络参数与基频有着密切的联系,利用基于径向基函数神经网络的联合谱包络基频变换方法,将谱包络参数与基频联合进行建模和转换,使得转换后的基频含有更多的说话人个性特征。最后,运用主、客观方法对获得的转换语音进行性能测试。实验表明,与主流的基于高斯混合模型的语音转换相比,使用自适应粒子群优化的径向基函数神经网络方法能够获得更好的转换性能,且更加适用于男声到女声的转换。     

Probabilistic self-organizing map and radial basis function networks

We propose in this paper a new learning algorithm probabilistic self-organizing map (PRSOM) using a probabilistic formalism for topological maps. This algorithm approximates the density distribution of the input set with a mixture of normal distributions. The unsupervised learning is based on the dynamic clusters principle and optimizes the likelihood function. A supervised version of this algorithm based on radial basis functions (RBF) is proposed. In order to validate the theoretical approach, we achieve regression tasks on simulated and real data using the PRSOM algorithm. Moreover, our results are compared with normalized Gaussian basis functions (NGBF) algorithm.     

一种优化的RBF神经网络模型用于网络流量预测

采用径向基RBF神经网络对网络流量数据的时间序列进行建模与预测。采用传统的学习算法对RBF网络训练时,对网络流量数据容易出现过拟合现象,提出了自适应量子粒子群优化AQPSO算法,用于训练RBF神经网络的基函数中心和宽度,并结合最小二乘法计算网络权值,改善了RBF神经网络的泛化能力。实验结果表明,采用AQPSO算法获得的RBF神经网络模型具有泛化能力强、稳定性良好的特点,在网络流量预测中有一定的实用价值。     

Optimal design of structures subjected to time history loading by swarm intelligence and an advanced metamodel

This paper proposes a new metamodeling framework that reduces the computational burden of the structural optimization against the time history loading. In order to achieve this, two strategies are adopted. In the first strategy, a novel metamodel consisting of adaptive neuro-fuzzy inference system (ANFIS), subtractive algorithm (SA), self organizing map (SOM) and a set of radial basis function (RBF) networks is proposed to accurately predict the time history responses of structures. The metamodel proposed is called fuzzy self-organizing radial basis function (FSORBF) networks. In this study, the most influential natural periods on the dynamic behavior of structures are treated as the inputs of the neural networks. In order to find the most influential natural periods from all the involved ones, ANFIS is employed. To train the FSORBF, the input–output samples are classified by a hybrid algorithm consisting of SA and SOM clusterings, and then a RBF network is trained for each cluster by using the data located. In the second strategy, particle swarm optimization (PSO) is employed to find the optimum design. Two building frame examples are presented to illustrate the effectiveness and practicality of the proposed methodology. A plane steel shear frame and a realistic steel space frame are designed for optimal weight using exact and approximate time history analyses. The numerical results demonstrate the efficiency and computational advantages of the proposed methodology.     

基于模糊自组织映射神经网络的故障诊断方法

在研究Kohonen自组织映射网络理论的基础上运用模糊理论方法建立了刹车系统模糊故障诊断模型。该模型只需选择足够的具有代表性的故障样本训练神经网络，将代表故障的信息输入给训练好的神经网络，根据神经网络的输出结果，就可以判断发生故障的类型。该模型除能识别已训练过的故障，还能识别未训练过的故障，并且聚类能力强、速度快，因此很符合复杂系统的故障诊断。     

A hierarchical neural model in short-term load forecasting

This paper proposes a novel neural model to the problem of short-term load forecasting (STLF). The neural model is made up of two self-organizing map (SOM) nets—one on top of the other. It has been successfully applied to domains in which the context information given by former events plays a primary role. The model was trained on load data extracted from a Brazilian electric utility, and compared to a multilayer perceptron (MLP) load forecaster. It was required to predict once every hour the electric load during the next 24 h. The paper presents the results, the conclusions, and points out some directions for future work.     

自组织多模型逼近性能分析与改进

针对基于自组织映射神经网络的非线性函数逼近,研究其方法和原理,指出它与一般前向神经网络在逼近原理上的不同．在此基础上,进一步研究该方法的逼近性能,分析其两个不足之处,进而提出一种提高逼近性能的改进神经网络训练策略．最后通过仿真实例验证了所得结论,表明了改进方法的有效性．     

Binary tree time adaptive self-organizing map

An adaptive hierarchical structure called “Binary Tree TASOM” (BTASOM) is proposed, which resembles a binary natural tree having nodes composed of Time Adaptive Self-Organizing Map (TASOM) networks. The standard TASOM is almost as slow as the standard SOM and has a fixed number of neurons. The BTASOM is proposed to make the TASOM fast and adaptive in the number of its neurons. The BTASOM is the first proposed hierarchical structure that uses a binary tree topology with TASOM networks. The number of levels of the BTASOM and the number of its nodes are adaptive to the accuracy demanded by the application through user-defined parameters. Two versions of the BTASOM are used here: the first version in which every node has only one neuron, and the second version in which every node has exactly two neurons. Both versions are tested with different distributions, stationary and nonstationary, for data representation. The experiments show that the BTASOM can work with both stationary and nonstationary environments while increasing the adaptability and speed of the standard TASOM. Several performance measures demonstrate the superiority of the proposed BTASOM in comparison with some other hierarchical SOM-based networks for clustering and input space approximation.     

Associative learning method in a hypercolumn model

We propose an associatively learnable hypercolumn model (AHCM). A hyper-column model is a self-organized, competitive, and hierarchical multilayer neural network. It is derived from the neocognitron by replacing each S cell and C cell with a two-layer hierarchical self-organizing map. The HCM can recognize images with variant object size, position, orientation and spatial resolution. However, feature maps may integrate some features extracted in the lower layer even if the features are extracted from input data which belong to different categories. The learning algorithm of the HCM causes this problem because it is an unsupervised learning used by a self-organizing map. An associative learning method is therefore introduced, which is derived from the HCM by appending associative signals and associative weights to traditional input data and connection weights, respectively. The AHCM was applied to hand-shape recognition. We found that the AHCM could generate an appropriate feature map and higher recognition accuracy compared with the HCM. This work was presented in part at the 11th International Symposium on Artificial Life and Robotics, Oita, Japan, January 23–25, 2006     

SOM网络的改进及其在储粮害虫分类中的应用

自组织特征映射神经网络(SOM网络)在分类方面存在的不足是训练时间长、分类精度不高以及学习过程容易发生振荡。为了改善SOM网络的分类性能,达到提高和分类精度的目的,提出了SOM网络的工作原理及算法,得出影响SOM网络分类性能的主要因素,包括学习率、初始权值、训练次数及邻域设置等,并分别提出了改进方法。利用改进后的SOM网络,通过3折分层交叉验证方法对储粮害虫数据进行分类验证,仿真实验结果表明,改进后的SOM分类器在学习速度和分类精度方面都得到了较大提高,证明提出的改进方法是有效的和可行的。     

基于神经网络的软测量技术及应用

软测量是一门新兴的工业技术，它借助现代估计理论构造模型推断出工程上难以检测的变量。本文提出了基于径向基函数神经网络（RBFNN）的软测量技术，并且结合工艺机理分析和过程数据关联，对其在轻柴油凝固点软测量的应用进行了研究。结果表明，RBFNN的良好的非线性动态建模能力使其在软测量中具有很大的应用潜力。