A Comparison of Deep Learning Architectures for the 3D Generation Data
JOURNAL OF BIOENGINEERING, TECHNOLOGIES AND HEALTH · 2022
DOI: 10.34178/jbth.v5i1.217 ↗Kurz gefasst
Fachartikel in der Zeitschrift JOURNAL OF BIOENGINEERING, TECHNOLOGIES AND HEALTH, 2022. Verfasst von Yasmin da Silva Bonfim und 3 weiteren Autor:innen.
Abstract (Originalsprache)
There is a need to identify the best artificial images for each use case faced with several Deep Learning architectures for generating them. Twelve models with different hyperparameters were created to compare several networks with the generative architectures Autoencoder, Variational Autoencoder, and Generative Adversarial Networks in the 3D MNIST dataset. After training, the models were compared with loss functions to assess the difference between the original and artificial data, so that greater complexity did not translate into better performance, indicating the Autoencoder models as the best cost-benefit.
Zitieren
APA
Bonfim, Y. D. S., Santos, G. S. R. L. D., Cruz, G. O. R., & Conterato, F. S. (2022). A Comparison of Deep Learning Architectures for the 3D Generation Data. JOURNAL OF BIOENGINEERING, TECHNOLOGIES AND HEALTH. https://doi.org/10.34178/jbth.v5i1.217
Vancouver
Bonfim YDS, Santos GSRLD, Cruz GOR, Conterato FS. A Comparison of Deep Learning Architectures for the 3D Generation Data. JOURNAL OF BIOENGINEERING, TECHNOLOGIES AND HEALTH. 2022. doi:10.34178/jbth.v5i1.217
BibTeX
@article{Bonfim2022,
author = {Bonfim, Yasmin da Silva and Santos, Gabriel Sete Ribeiro Lago dos and Cruz, Gustavo Oliveira Ramos and Conterato, Flávio Santos},
title = {A Comparison of Deep Learning Architectures for the 3D Generation Data},
journal = {JOURNAL OF BIOENGINEERING, TECHNOLOGIES AND HEALTH},
year = {2022},
doi = {10.34178/jbth.v5i1.217}
}
EUVIMED