摘要
研究了前向两层径基函数 ( RBF)网络和前向两层线性基本函数 ( LBF)网络的分类机理及其结构与初始参数优化确定方法 ,提出了 Guassian核函数的中心和宽度应通过学习自动确定 ,在学习过程中根据错分样本自身的类别和被错分入的类别自动生成新的核函数 ,并根据新增核函数对测试集的作用自动删除多余核函数的观点 ,从理论上阐明了采用 Sigmoid活化函数的两层LBF网络的分类阈值为 0 .5 ,进而提出了由两层 RBF网络和两层 LBF网络组成的前向 RBF神经网络——
The classification mechanisms of feedforward two layered radial basis function(RBF) and linear basis function(LBF) networks as well as the methods of optimally determining their structures and initial parameters were studied. The viewpoints were presented that the centers and widths of Gaussian kernels in RBF networks should be determined by a self learning procedure, that a few new kernels be naturally come into being according to which class some labeled patterns are misclassified to, and going a step f...
出处
《华东理工大学学报(自然科学版)》
CAS
CSCD
北大核心
2001年第6期677-683,共7页
Journal of East China University of Science and Technology
基金
华东理工大学生物反应器工程国家重点实验室开放课题( SK0 0 -0 7)