Towards a configurable and non-hierarchical search space for NAS

Neural Architecture Search (NAS) outperforms handcrafted Neural Network (NN) design. However, current NAS methods generally use hard-coded search spaces, and predefined hierarchical architectures. As a consequence, adapting them to a new problem can be cumbersome, and it is hard to know which of the...

Full description

Bibliographic Details

Published in:	Neural networks Vol. 180; p. 106700
Main Authors:	Perrin, Mathieu, Guicquero, William, Paille, Bruno, Sicard, Gilles
Format:	Journal Article
Language:	English
Published:	United States Elsevier Ltd 01.12.2024
Subjects:	Algorithms Bayes Theorem Bayesian optimization Convolutional neural network Humans Neural architecture search Neural Networks, Computer Normal Distribution Wasserstein autoencoder Wasserstein autoencoder Neural architecture search Bayesian optimization Convolutional neural network
ISSN:	0893-6080, 1879-2782, 1879-2782
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!