Feedforward networks with one hidden layer and their rates of approximation

被引：0

作者：

Hlavackova, K ^{[1
]}

机构：

[1] Acad Sci Czech Republ, Inst Comp Sci, Prague 18207 8, Czech Republic

来源：

UKACC INTERNATIONAL CONFERENCE ON CONTROL '98, VOLS I&II | 1998年

关键词：

feed-forward network; rates of approximation; activation function; polynomial and exponential complexity;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We present an overview of some rates of approximation with respect to various computational units in the hidden layer of a one-layered feed-forward neural network. The problem of estimating the number of units in the hidden layer is examined to ensure a given degree of approximation for a given function class. The results are discussed in terms of their complexity and functional characteristics.

引用

页码：727 / 732

页数：6