Back to Search Start Over

Efficient Network Architecture Search Using Hybrid Optimizer.

Authors :
Wang, Ting-Ting
Chu, Shu-Chuan
Hu, Chia-Cheng
Jia, Han-Dong
Pan, Jeng-Shyang
Source :
Entropy; May2022, Vol. 24 Issue 5, pN.PAG-N.PAG, 20p
Publication Year :
2022

Abstract

Manually designing a convolutional neural network (CNN) is an important deep learning method for solving the problem of image classification. However, most of the existing CNN structure designs consume a significant amount of time and computing resources. Over the years, the demand for neural architecture search (NAS) methods has been on the rise. Therefore, we propose a novel deep architecture generation model based on Aquila optimization (AO) and a genetic algorithm (GA). The main contributions of this paper are as follows: Firstly, a new encoding strategy representing the CNN coding structure is proposed, so that the evolutionary computing algorithm can be combined with CNN. Secondly, a new mechanism for updating location is proposed, which incorporates three typical operators from GA cleverly into the model we have designed so that the model can find the optimal solution in the limited search space. Thirdly, the proposed method can deal with the variable-length CNN structure by adding skip connections. Fourthly, combining traditional CNN layers and residual blocks and introducing a grouping strategy provides greater possibilities for searching for the optimal CNN structure. Additionally, we use two notable datasets, consisting of the MNIST and CIFAR-10 datasets for model evaluation. The experimental results show that our proposed model has good results in terms of search accuracy and time. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
10994300
Volume :
24
Issue :
5
Database :
Complementary Index
Journal :
Entropy
Publication Type :
Academic Journal
Accession number :
157190619
Full Text :
https://doi.org/10.3390/e24050656