Performance prediction based on neural architecture features

Performance prediction based on neural architecture features

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...

Full description

Bibliographic Details
Main Authors: Duo Long, Shizhou Zhang, Yanning Zhang
Format: Article
Language:English
Published: Wiley 2020-04-01
Series:Cognitive Computation and Systems
Subjects:
neural nets
regression analysis
learning (artificial intelligence)
n-grams model
architecture textual description
extracted neural architecture features
appropriate regression model
modelling learning curve
performance prediction method
neural architecture search
candidate neural networks
high-performance network architecture
optimising hyperparameters
training steps
sequence features
chain-structured neural architecture
Online Access:https://digital-library.theiet.org/content/journals/10.1049/ccs.2019.0024

Similar Items

Similar Items