期刊
JOURNAL OF ECONOMIC DYNAMICS & CONTROL
卷 28, 期 1, 页码 183-187出版社
ELSEVIER
DOI: 10.1016/S0165-1889(02)00157-4
关键词
Feedforward artificial neural network; Activation function; Squashing function; Sigmoid function
类别
A limited number of activation functions have been utilized in practice for feedforward artificial neural networks. A class of sigmoidal functions is defined and another function, which is the envelope of the derivatives of the members of the defined class, is shown to be sigmoidal. The functions defined are shown to satisfy the requirements of the universal approximation theorem(s). (C) 2003 Published by Elsevier Science B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据