Study of the Effect of Combining Activation Functions in a Convolutional Neural Network

Convolutional Neural Networks (CNN’s) have proven to be an effective approach for solving image classification problems. The output, the accuracy and the computational efficiency of a CNN are determined mainly by the architecture, the convolutional filters, and the activation functions. Based o...

Descripció completa

Guardat en:

Dades bibliogràfiques
Autor principal:	Vergara Villegas, Osslan Osiris
Altres autors:	Sossa Azuela, Juan Humberto, Cruz Sanchez, Vianey Guadalupe, Ochoa Domínguez, Humberto, Nandayapa, Manuel
Format:	Artículo
Idioma:	English
Publicat:	2020
Matèries:	Activation function Convolutional neural network Modified National Institute of Standards and Technology Fashion Modified National Institute of Standards and Technology Sigmoid Rectified linear unit info:eu-repo/classification/cti/7
Accés en línia:	https://latamt.ieeer9.org/index.php/transactions/article/view/4134
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!

Sigues el primer a deixar un comentari!

Study of the Effect of Combining Activation Functions in a Convolutional Neural Network

Ítems similars