Performance prediction based on neural architecture features
Cognitive Computation and Systems · 2020
DOI: 10.1049/ccs.2019.0024 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cognitive Computation and Systems, 2020. Verfasst von Duo Long und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).
Abstract (Originalsprache)
Neural Architecture Search (NAS) usually requires to train quantities of candidate neural networks on a dataset for choosing a high‐performance network architecture and optimising hyperparameters, which is very time consuming and computationally expensive. In order to resolve the issue, the authors try to use a performance prediction method to predict the model performance with little or even no training steps. They assume that the performance is determined once the architecture and other hyperparameters are chosen. So they first extract the sequence features of the chain‐structured neural architecture by introducing the N‐grams model to process architecture textual description. Subsequently, based on the extracted neural architecture features, they use the appropriate regression model to predict validation accuracies for a modelling learning curve. Through a series of experimental comparisons, they verify the effectiveness of the authors’ proposed performance prediction method and the effective acceleration of the NAS process.
Zitieren
APA
Long, D., Zhang, S., & Zhang, Y. (2020). Performance prediction based on neural architecture features. Cognitive Computation and Systems. https://doi.org/10.1049/ccs.2019.0024
Vancouver
Long D, Zhang S, Zhang Y. Performance prediction based on neural architecture features. Cognitive Computation and Systems. 2020. doi:10.1049/ccs.2019.0024
BibTeX
@article{Long2020,
author = {Long, Duo and Zhang, Shizhou and Zhang, Yanning},
title = {Performance prediction based on neural architecture features},
journal = {Cognitive Computation and Systems},
year = {2020},
doi = {10.1049/ccs.2019.0024}
}
EUVIMED