New activation functions for single layer feedforward neural network

作者：

Highlights：

• Activation functions affect the performance of an artificial neural network.

• New activation functions can combine the advantages of predefined ones.

• New activation functions perform better than the older ones.

摘要

•Activation functions affect the performance of an artificial neural network.•New activation functions can combine the advantages of predefined ones.•New activation functions perform better than the older ones.

论文关键词：Artificial Neural Network,Activation function,Generalized swish,ReLU-swish,Triple-state swish

论文评审过程：Received 10 December 2019, Revised 20 August 2020, Accepted 4 September 2020, Available online 18 September 2020, Version of Record 1 October 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113977