Neural networks with asymmetric activation function for function approximation
Gecynalda Soares da Silva Gomes, Teresa B. Ludermir, Leandro Maciel Almeida · 2009
The choice of activation functions may strongly influence complexity and performance of neural networks. However a limited number of activation functions have been used in practice for artificial neural networks. We propose the use of two new functions as asymmetric activation functions of neural networks and these defined functions are shown to satisfy the requirements of the universal approximation theorem.