ECToNAS: Evolutionary Cross-Topology Neural Architecture Search

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Schiessler, Elisabeth J., Aydin, Roland C., Cyron, Christian J.
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition Neural and Evolutionary Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866917608296546304
author	Schiessler, Elisabeth J. Aydin, Roland C. Cyron, Christian J.
author_facet	Schiessler, Elisabeth J. Aydin, Roland C. Cyron, Christian J.
contents	We present ECToNAS, a cost-efficient evolutionary cross-topology neural architecture search algorithm that does not require any pre-trained meta controllers. Our framework is able to select suitable network architectures for different tasks and hyperparameter settings, independently performing cross-topology optimisation where required. It is a hybrid approach that fuses training and topology optimisation together into one lightweight, resource-friendly process. We demonstrate the validity and power of this approach with six standard data sets (CIFAR-10, CIFAR-100, EuroSAT, Fashion MNIST, MNIST, SVHN), showcasing the algorithm's ability to not only optimise the topology within an architectural type, but also to dynamically add and remove convolutional cells when and where required, thus crossing boundaries between different network types. This enables researchers without a background in machine learning to make use of appropriate model types and topologies and to apply machine learning methods in their domains, with a computationally cheap, easy-to-use cross-topology neural architecture search framework that fully encapsulates the topology optimisation within the training process.
format	Preprint
id	arxiv_https___arxiv_org_abs_2403_05123
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	ECToNAS: Evolutionary Cross-Topology Neural Architecture Search Schiessler, Elisabeth J. Aydin, Roland C. Cyron, Christian J. Machine Learning Computer Vision and Pattern Recognition Neural and Evolutionary Computing We present ECToNAS, a cost-efficient evolutionary cross-topology neural architecture search algorithm that does not require any pre-trained meta controllers. Our framework is able to select suitable network architectures for different tasks and hyperparameter settings, independently performing cross-topology optimisation where required. It is a hybrid approach that fuses training and topology optimisation together into one lightweight, resource-friendly process. We demonstrate the validity and power of this approach with six standard data sets (CIFAR-10, CIFAR-100, EuroSAT, Fashion MNIST, MNIST, SVHN), showcasing the algorithm's ability to not only optimise the topology within an architectural type, but also to dynamically add and remove convolutional cells when and where required, thus crossing boundaries between different network types. This enables researchers without a background in machine learning to make use of appropriate model types and topologies and to apply machine learning methods in their domains, with a computationally cheap, easy-to-use cross-topology neural architecture search framework that fully encapsulates the topology optimisation within the training process.
title	ECToNAS: Evolutionary Cross-Topology Neural Architecture Search
topic	Machine Learning Computer Vision and Pattern Recognition Neural and Evolutionary Computing
url	https://arxiv.org/abs/2403.05123