Automated Design of Deep Neural Networks
Document type :
Compte-rendu et recension critique d'ouvrage
DOI :
Title :
Automated Design of Deep Neural Networks
Author(s) :
Talbi, El-Ghazali [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Optimisation de grande taille et calcul large échelle [BONUS]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Optimisation de grande taille et calcul large échelle [BONUS]
Journal title :
ACM Computing Surveys
Pages :
1-37
Publisher :
Association for Computing Machinery
Publication date :
2022-04
ISSN :
0360-0300
HAL domain(s) :
Informatique [cs]/Intelligence artificielle [cs.AI]
English abstract : [en]
In recent years, research in applying optimization approaches in the automatic design of deep neural networks has become increasingly popular. Although various approaches have been proposed, there is a lack of a comprehensive ...
Show more >In recent years, research in applying optimization approaches in the automatic design of deep neural networks has become increasingly popular. Although various approaches have been proposed, there is a lack of a comprehensive survey and taxonomy on this hot research topic. In this article, we propose a unified way to describe the various optimization algorithms that focus on common and important search components of optimization algorithms: representation, objective function, constraints, initial solution(s), and variation operators. In addition to large-scale search space, the problem is characterized by its variable mixed design space, it is very expensive, and it has multiple blackbox objective functions. Hence, this unified methodology has been extended to advanced optimization approaches, such as surrogate-based, multi-objective, and parallel optimization.Show less >
Show more >In recent years, research in applying optimization approaches in the automatic design of deep neural networks has become increasingly popular. Although various approaches have been proposed, there is a lack of a comprehensive survey and taxonomy on this hot research topic. In this article, we propose a unified way to describe the various optimization algorithms that focus on common and important search components of optimization algorithms: representation, objective function, constraints, initial solution(s), and variation operators. In addition to large-scale search space, the problem is characterized by its variable mixed design space, it is very expensive, and it has multiple blackbox objective functions. Hence, this unified methodology has been extended to advanced optimization approaches, such as surrogate-based, multi-objective, and parallel optimization.Show less >
Language :
Anglais
Popular science :
Non
Collections :
Source :