期刊
NEUROCOMPUTING
卷 56, 期 -, 页码 447-454出版社
ELSEVIER
DOI: 10.1016/j.neucom.2003.08.005
关键词
feedforward artificial neural networks; sigmoidal activation; squashing function; self-adaptation
The universal approximation results for sigmoidal feedforward artificial neural networks do not recommend a preferred activation function. We investigated the null hypothesis that there is no preferred activation function from a class of activation functions. Our result indicates that there may exist a preferred activation that depends on the task to be solved and the specific data set used for training. The results allow us to conjecture that training algorithms that adapt the activation function may lead to faster training than those that do not. (C) 2003 Published by Elsevier 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