A class +1 sigmoidal activation functions for FFANNs

详细信息	查看全文 | 推荐本文 |

• 作者：Singh ; Yogesh ; Chandra ; Pravin
• 关键词：Feedforward artificial neural network ; Activation function ; Squashing function ; Sigmoid function
• 刊名：Journal of Economic Dynamics and Control
• 出版年：2003
• 期刊代码：37_01651889
• 类别：eco
• 出版时间：October, 2003
• 卷：28
• 期：1
• 页码：183-187
• 文件大小：169 K

摘要

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).