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

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Neural architecture search using particle swarm and ant colony optimization

Lankford, Séamus and Grimes, Diarmuid orcid logoORCID: 0000-0001-5551-6504 (2020) Neural architecture search using particle swarm and ant colony optimization. In: AICS 2020 Artificial Intelligence and Cognitive Science, 7-8 Dec 2020, Dublin, Ireland.

Abstract
Neural network models have a number of hyperparameters that must be chosen along with their architecture. This can be a heavy burden on a novice user, choosing which architecture and what values to assign to parameters. In most cases, default hyperparameters and architectures are used. Significant improvements to model accuracy can be achieved through the evaluation of multiple architectures. A process known as Neural Architecture Search (NAS) may be applied to automatically evaluate a large number of such architectures. A system integrating open source tools for Neural Architecture Search (OpenNAS), in the classification of images, has been developed as part of this research. OpenNAS takes any dataset of grayscale, or RBG images, and generates Convolutional Neural Network (CNN) architectures based on a range of metaheuristics using either an AutoKeras, a transfer learning or a Swarm Intelligence (SI) approach. Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) are used as the SI algorithms. Furthermore, models developed through such metaheuristics may be combined using stacking ensembles. In the context of this paper, we focus on training and optimizing CNNs using the Swarm Intelligence (SI) components of OpenNAS. Two major types of SI algorithms, namely PSO and ACO, are compared to see which is more effective in generating higher model accuracies. It is shown, with our experimental design, that the PSO algorithm performs better than ACO. The performance improvement of PSO is most notable with a more complex dataset. As a baseline, the performance of fine-tuned pre-trained models is also evaluated.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:AutoML; NAS; Swarm Intelligence; PSO; ACO; CNN
Subjects:UNSPECIFIED
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Published in: Proceedings of The 28th Irish Conference on Artificial Intelligence and Cognitive Science. 2771. CEUR-WS.
Publisher:CEUR-WS
Official URL:https://ceur-ws.org/Vol-2771/AICS2020_paper_30.pdf
Copyright Information:© 2020 The Authors
Funders:SFI Research Centres Programme (Grant 13/RC/2016), European Regional Development Fund, Munster Technological University
ID Code:28344
Deposited On:19 May 2023 11:37 by Seamus Lankford . Last Modified 19 May 2023 11:37
Documents

Full text available as:

[thumbnail of slankford-aiai.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