Regularized Evolution for Macro Neural Architecture Search - Artificial Intelligence Applications and Innovations Access content directly
Conference Papers Year : 2020

Regularized Evolution for Macro Neural Architecture Search

George Kyriakides
  • Function : Author
  • PersonId : 1056865

Abstract

Neural Architecture Search is becoming an increasingly popular research field and method to design deep learning architectures. Most research focuses on searching for small blocks of deep learning operations, or micro-search. This method yields satisfactory results but demands prior knowledge of the macro architecture’s structure. Generally, methods that do not utilize macro structure knowledge perform worse but are able to be applied to datasets of completely new domains. In this paper, we propose a macro NAS methodology which utilizes concepts of Regularized Evolution and Macro Neural Architecture Search (DeepNEAT), and apply it to the Fashion-MNIST dataset. By utilizing our method, we are able to produce networks that outperform other macro NAS methods on the dataset, when the same post-search inference methods are used. Furthermore, we are able to achieve 94.46% test accuracy, while requiring considerably less epochs to fully train our network.
Fichier principal
Vignette du fichier
500087_1_En_10_Chapter.pdf (561.2 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04060681 , version 1 (06-04-2023)

Licence

Attribution

Identifiers

Cite

George Kyriakides, Konstantinos Margaritis. Regularized Evolution for Macro Neural Architecture Search. 16th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2020, Neos Marmaras, Greece. pp.111-122, ⟨10.1007/978-3-030-49186-4_10⟩. ⟨hal-04060681⟩
9 View
1 Download

Altmetric

Share

Gmail Facebook X LinkedIn More