Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Open-source neural architecture search with ensemble and pre-trained networks

Lankford, Séamus (2021) Open-source neural architecture search with ensemble and pre-trained networks. International Journal of Modeling and Optimization, 11 (2). pp. 33-41. ISSN 2010-3697

Abstract
The training and optimization of neural networks, using pre-trained, super learner and ensemble approaches is explored. Neural networks, and in particular Convolutional Neural Networks (CNNs), are often optimized using default parameters. Neural Architecture Search (NAS) enables multiple architectures to be evaluated prior to selection of the optimal architecture. Our contribution is to develop, and make available to the community, a system that integrates open source tools for the neural architecture search (OpenNAS) of image classification models. OpenNAS takes any dataset of grayscale, or RGB images, and generates the optimal CNN architecture. Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO) and pre-trained models serve as base learners for ensembles. Meta learner algorithms are subsequently applied to these base learners and the ensemble performance on image classification problems is evaluated. Our results show that a stacked generalization ensemble of heterogeneous models is the most effective approach to image classification within OpenNAS.
Metadata
Item Type:Article (Published)
Refereed:Yes
Uncontrolled Keywords:AutoML; transfer learning; pre-trained models; ensemble; stacking; super learner; PSO; ACO; CNN
Subjects:Computer Science > Machine learning
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Publisher:International Association of Computer Science and Information Technology (IACSIT)
Official URL:https://doi.org/10.7763/IJMO.2021.V11.774
Copyright Information:© 2021 The Author.
Funders:Science Foundation Ireland(SFI) Research Centres Programme (Grant 13/RC/2016), European Regional Development Fund, Munster Technological University
ID Code:28350
Deposited On:19 May 2023 12:54 by Seamus Lankford . Last Modified 19 May 2023 12:54
Documents

Full text available as:

[thumbnail of slankford-imjo.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution 4.0
1MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record