基于RBF神经网络结构混合优化的数字识别  

Digital Identification of RBF Neutral Network Based on Structure Hybrid Optimization

作　　者：张秀玲[1,2] 付栋[1] 李海滨[1] 来永进 王振臣[1] 

机构地区：[1]燕山大学河北省工业计算机控制工程重点实验室,河北秦皇岛066004 [2]国家冷轧板带装备及工艺工程技术研究中心,河北秦皇岛066004

出　　处：《沈阳大学学报（自然科学版）》2015年第3期214-221,共8页Journal of Shenyang University：Natural Science

基　　金：国家自然科学基金资助项目(61007003)

摘　　要：以数字识别为应用背景构建RBF神经网络结构,首先把最近邻聚类算法与k-均值聚类算法应用于RBF神经网络隐层中心个数及中心值的确定中,实现了隐层中心个数与中心值的自适应获取;然后将遗传算法与伪逆法相结合来确定隐层中心宽度及输出权值;最后对混合优化的神经网络与传统的基于中心自组织学习算法优化的网络进行仿真实验.实验中使用未加噪声和添加噪声的数字样本对网络进行测试,与传统优化方法对比结果表明,应用该混合学习算法构建的神经网络具有识别能力强、计算量小的优点.The digital recognition is taken as the application background to construct RBF neural network.Firstly,the nearest neighbor clustering algorithm and k-means clustering algorithm are applied to determine RBF neural network hidden layer center＇s number and value adaptively;then genetic algorithm and pseudo inverse method are combined to determine the hidden layer center＇s width and output weight;finally,based on hybrid optimization and the network based on center selforganizing learning algorithm,the experiment is finished by using the neural network.Stimulation results show that the network has the advantages of good recognition ability and small calculation quantity,which is constructed by using hybrid learning algorithm without noise samples and noise samples to test network.

关 键 词：径向基函数神经网络(RBFNN) 聚类 遗传算法 数字识别 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]