These processors requirement for performance make it possible the elementary function as the independently arithmetic component.
这些处理器对性能的要求使得除法和基本函数功能部件作为其中独立的运算部件成为可能。
Based on researching into the classification mechanisms of feedforward single-layer radial basis function (RBF) and linear basis function (LBF) networks,the author presents the viewpoints that the RBF centers and widths should be determined through a self-learning procedure,that some new kernels naturally come into being according to which class the labeled patterns are misclassified to.
研究了前向单层径基函数 (RBF)网络和前向单层线性基本函数 (LBF)网络的分类机理 ,提出了RBF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被错分入的类别自动生成新的核函数这一观点 。
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.
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 。
, dissecting mappings on the test functions space,the usual distributions was generalized to pan-linear distributions,and then the forms,structure and basic differential properties of pan-linear distributions were discussed.
将一类非线性映射即解剖映射作用在基本函数空间上,定义了泛线性广义函数,从而将线性广义函数推广到泛线性广义函数上。