Automated Design of Deep Neural Networks
Type de document :
Article dans une revue scientifique
DOI :
Titre :
Automated Design of Deep Neural Networks
Auteur(s) :
Talbi, El-Ghazali [Auteur]
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]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Titre de la revue :
ACM Computing Surveys
Pagination :
1-37
Éditeur :
Association for Computing Machinery
Date de publication :
2022-04
ISSN :
0360-0300
Discipline(s) HAL :
Informatique [cs]/Intelligence artificielle [cs.AI]
Résumé en anglais : [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 ...
Lire la suite >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.Lire moins >
Lire la suite >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.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :