Agent Based Model for AUTODL Optimisation

Aroua Hedhili, Aroua Hedhili, Imen Khelfa, Imen Khelfa

2024

Abstract

Auto Deep Learning (AUTODL) has witnessed remarkable growth and advancement in recent years, simplifying neural network model selection, hyperparameter tuning, and model evaluation, thereby increasing accessibility for users with limited deep learning expertise. Nevertheless, certain performance limitations persist, notably in the realm of computational resource utilization. In response, we introduce an agent-based AUTODL methodology that leverages multi-objective optimization principles and collective intelligence to create high-performing artificial neural networks. Our experimental results confirm the effectiveness of this approach across various criteria, including accuracy, computational inference time, and resource consumption.

Paper Citation

in Harvard Style

Hedhili A. and Khelfa I. (2024). Agent Based Model for AUTODL Optimisation. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 568-575. DOI: 10.5220/0012371700003636

in Bibtex Style

@conference{icaart24,
author={Aroua Hedhili and Imen Khelfa},
title={Agent Based Model for AUTODL Optimisation},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={568-575},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012371700003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Agent Based Model for AUTODL Optimisation
SN - 978-989-758-680-4
AU - Hedhili A.
AU - Khelfa I.
PY - 2024
SP - 568
EP - 575
DO - 10.5220/0012371700003636
PB - SciTePress