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...

Celý popis

Uloženo v:

Podrobná bibliografie
Hlavní autor:	Vergara Villegas, Osslan Osiris
Další autoři:	Sossa Azuela, Juan Humberto, Cruz Sanchez, Vianey Guadalupe, Ochoa Domínguez, Humberto, Nandayapa, Manuel
Médium:	Artículo
Jazyk:	English
Vydáno:	2020
Témata:	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
On-line přístup:	https://latamt.ieeer9.org/index.php/transactions/article/view/4134
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo otaguje tento záznam!

Buďte první, kdo okomentuje tento záznam!

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

Podobné jednotky