Skip to Main content Skip to Navigation
Journal articles

Automated Design of Deep Neural Networks

El-Ghazali Talbi 1, 2, 3 
1 BONUS - Optimisation de grande taille et calcul large échelle
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : 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.
Document type :
Journal articles
Complete list of metadata

https://hal.inria.fr/hal-03339896
Contributor : TALBI El-Ghazali Connect in order to contact the contributor
Submitted on : Thursday, September 9, 2021 - 5:17:29 PM
Last modification on : Friday, July 8, 2022 - 10:04:27 AM

Identifiers

Citation

El-Ghazali Talbi. Automated Design of Deep Neural Networks. ACM Computing Surveys, Association for Computing Machinery, 2021, 54 (2), pp.1-37. ⟨10.1145/3439730⟩. ⟨hal-03339896⟩

Share

Metrics

Record views

29