EUVIMEDEUVIMED entdecken
Crossref

A Review of Evolutionary Deep Neural Architecture Search with Performance Predictor

Zenglin QIAO, Xinchao ZHAO, Lingyu WU

Bulletin of Chinese Applied Mathematics · 2023

DOI: 10.48014/bcam.20230822002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bulletin of Chinese Applied Mathematics, 2023. Verfasst von Zenglin QIAO und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated design of deep neural networks using performance predictor has become a hot topic in current research. Neural architecture search (NAS) methods can be used to enable automatic design of neural network structures by defining different search spaces, search strategies, or optimization strategies. Evolutionary computation by many researchers as the search strategy for NAS, which is called evolutionary NAS (ENAS) . However, ENAS is time-consuming in evaluating the performance of network structures, which hinders the development of ENAS. Therefore, predicting network architecture performance using performance predictor can improve ENAS search speed and save computational resources. This paper summarizes several ENAS methods that utilize performance predictor, and discusses an outlook on search space, search strategies, and the future directions of ENAS assisted by performance predictor.

Zitieren

APA

QIAO, Z., ZHAO, X., & WU, L. (2023). A Review of Evolutionary Deep Neural Architecture Search with Performance Predictor. Bulletin of Chinese Applied Mathematics. https://doi.org/10.48014/bcam.20230822002

Vancouver

QIAO Z, ZHAO X, WU L. A Review of Evolutionary Deep Neural Architecture Search with Performance Predictor. Bulletin of Chinese Applied Mathematics. 2023. doi:10.48014/bcam.20230822002

BibTeX
@article{QIAO2023,
  author = {QIAO, Zenglin and ZHAO, Xinchao and WU, Lingyu},
  title = {A Review of Evolutionary Deep Neural Architecture Search with Performance Predictor},
  journal = {Bulletin of Chinese Applied Mathematics},
  year = {2023},
  doi = {10.48014/bcam.20230822002}
}
Kostenlos starten →