review · ACM Computing Surveys · 2021
Automated Design of Deep Neural Networks
Cited by 42Abstract and details only
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.
Cite this paper
Talbi, E. (2021). Automated Design of Deep Neural Networks. ACM Computing Surveys, 54(2), 1–37. https://doi.org/10.1145/3439730
Talbi, El‐Ghazali. “Automated Design of Deep Neural Networks.” ACM Computing Surveys, vol. 54, no. 2, 2021, pp. 1–37, https://doi.org/10.1145/3439730.
Talbi, El‐Ghazali. 2021. “Automated Design of Deep Neural Networks.” ACM Computing Surveys 54 (2): 1–37. https://doi.org/10.1145/3439730.
Talbi, E. (2021) ‘Automated Design of Deep Neural Networks’, ACM Computing Surveys, 54(2), pp. 1–37. Available at: https://doi.org/10.1145/3439730.
@article{talbi2021automated,
title = {{Automated Design of Deep Neural Networks}},
author = {Talbi, El‐Ghazali},
journal = {ACM Computing Surveys},
volume = {54},
number = {2},
pages = {1--37},
year = {2021},
doi = {10.1145/3439730}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.