Adaptive hybrid activation function for deep neural networks

Adaptive hybrid activation function for deep neural networks

The adaptive hybrid activation function (AHAF) is proposed that combines the properties of the rectifier units and the squashing functions. The proposed function can be used as a drop-in replacement for ReLU, SiL and Swish activations for deep neural networks and can evolve to one of such functions...

Full description

Bibliographic Details
Main Authors: Yevgeniy Bodyanskiy, Serhii Kostiuk
Format: Article
Language:Ukrainian
Published: Igor Sikorsky Kyiv Polytechnic Institute 2022-04-01
Series:Sistemnì Doslìdženâ ta Informacìjnì Tehnologìï
Subjects:
adaptive hybrid activation function
double-stage parameter turning process
deep neural networks
Online Access:http://journal.iasa.kpi.ua/article/view/259203

Internet

http://journal.iasa.kpi.ua/article/view/259203

Similar Items