Activation Functions for Convolutional Neural Networks: Proposals and Experimental Study.
IEEE Trans Neural Netw Learn Syst
; 34(3): 1478-1488, 2023 Mar.
Article
en En
| MEDLINE
| ID: mdl-34428161
ABSTRACT
Activation functions lie at the core of every neural network model from shallow to deep convolutional neural networks. Their properties and characteristics shape the output range of each layer and, thus, their capabilities. Modern approaches rely mostly on a single function choice for the whole network, usually ReLU or other similar alternatives. In this work, we propose two new activation functions and analyze their properties and compare them with 17 different function proposals from recent literature on six distinct problems with different characteristics. The objective is to shed some light on their comparative performance. The results show that the proposed functions achieved better performance than the most commonly used ones.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Tipo de estudio:
Prognostic_studies
Idioma:
En
Revista:
IEEE Trans Neural Netw Learn Syst
Año:
2023
Tipo del documento:
Article