A Machine Learning Approach for Face Mask Detection System with AdamW Optimizer
Journal of Applied Technology and Innovation · 01.09.2023 · 7 (3)
DOI: 10.65136/jati.v7i1.131 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Technology and Innovation, online erschienen am 01.09.2023. Verfasst von Leong Kah Meng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
As Adam optimizer’s learning rate decay hyperparameter has recently been deprecated, this journal article focuses not only on providing an alternate optimizer but also on comparing the performance of the said optimizer, AdamW, with the Adam optimizer using a face mask detection model. This study experiments with different weight decay values and finds that a weight decay of 0.00009 with the AdamW optimizer consistently achieves a 98% accuracy rate. Aside from that, this study also discusses the differences between Adam with L2-regularization and AdamW on how the weight decay is decoupled from the Adam optimizer’s gradient-based update that impacts the performance of AdamW. Overall, the study provides insights to those new to AdamW and looking for a starting point in optimizing deep learning models.
Zitieren
APA
Meng, L. K., Yi, H. H., Wei, N. B., Xin, L. J., & Salam, Z. A. A. (2023). A Machine Learning Approach for Face Mask Detection System with AdamW Optimizer. Journal of Applied Technology and Innovation, 7(3). https://doi.org/10.65136/jati.v7i1.131
Vancouver
Meng LK, Yi HH, Wei NB, Xin LJ, Salam ZAA. A Machine Learning Approach for Face Mask Detection System with AdamW Optimizer. Journal of Applied Technology and Innovation. 2023;7(3). doi:10.65136/jati.v7i1.131
BibTeX
@article{Meng2023,
author = {Meng, Leong Kah and Yi, Ho Hooi and Wei, Ng Bo and Xin, Lim Jia and Salam, Zailan Arabee Abdul},
title = {A Machine Learning Approach for Face Mask Detection System with AdamW Optimizer},
journal = {Journal of Applied Technology and Innovation},
year = {2023},
volume = {7},
number = {3},
doi = {10.65136/jati.v7i1.131}
}
EUVIMED