摘要
给出M-P神经元模型的几何意义,这个几何的铨释,给神经元一个非常直观的理解,利用这个直观的理解,给出两个颇为有趣的应用:(1)用此法给出三层前向神经网络的学习能力的基本定理的新的证明;(2)给出前向网络的拓扑结构设计的新方法.
In this paper, a geometrical representation of M P neural model is presented. From the representation,a clear visual picture and interpretation of the model can be seen. Two interesting applications based on the interpretation are discussed. They are (1) a new design principle of feedforward neural networks, and (2) a new proof of mapping abilities of three layer feedforward neural networks.
出处
《软件学报》
EI
CSCD
北大核心
1998年第5期334-338,共5页
Journal of Software
基金
国家自然科学基金
国家863高科技项目基金
国家"攀登"计划基金
关键词
神经网络
领域覆盖
可测函数
M-P神经元模型
Feedforward neural networks, neighborhood covering, measurable functions.