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

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!

Podobné jednotky

Podobné jednotky