Automated CNN Architectural Design: A Simple and Efficient Methodology for Computer Vision Tasks
Mathematics · 24.02.2023 · 11 (5) · 1141
DOI: 10.3390/math11051141 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 24.02.2023. Verfasst von Ali Al Bataineh und 3 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Convolutional neural networks (CNN) have transformed the field of computer vision by enabling the automatic extraction of features, obviating the need for manual feature engineering. Despite their success, identifying an optimal architecture for a particular task can be a time-consuming and challenging process due to the vast space of possible network designs. To address this, we propose a novel neural architecture search (NAS) framework that utilizes the clonal selection algorithm (CSA) to automatically design high-quality CNN architectures for image classification problems. Our approach uses an integer vector representation to encode CNN architectures and hyperparameters, combined with a truncated Gaussian mutation scheme that enables efficient exploration of the search space. We evaluated the proposed method on six challenging EMNIST benchmark datasets for handwritten digit recognition, and our results demonstrate that it outperforms nearly all existing approaches. In addition, our approach produces state-of-the-art performance while having fewer trainable parameters than other methods, making it low-cost, simple, and reusable for application to multiple datasets.
Zitieren
APA
Bataineh, A. A., Kaur, D., Al-khassaweneh, M., & Al-sharoa, E. (2023). Automated CNN Architectural Design: A Simple and Efficient Methodology for Computer Vision Tasks. Mathematics, 11(5), 1141. https://doi.org/10.3390/math11051141
Vancouver
Bataineh AA, Kaur D, Al-khassaweneh M, Al-sharoa E. Automated CNN Architectural Design: A Simple and Efficient Methodology for Computer Vision Tasks. Mathematics. 2023;11(5):1141. doi:10.3390/math11051141
BibTeX
@article{Bataineh2023,
author = {Bataineh, Ali Al and Kaur, Devinder and Al-khassaweneh, Mahmood and Al-sharoa, Esraa},
title = {Automated CNN Architectural Design: A Simple and Efficient Methodology for Computer Vision Tasks},
journal = {Mathematics},
year = {2023},
volume = {11},
number = {5},
pages = {1141},
doi = {10.3390/math11051141}
}
EUVIMED