Genetic algorithm based hyper-parameters optimization for transfer convolutional neural network

Chen Li; JinZhe Jiang; YaQian Zhao; RenGang Li; EnDong Wang; Xin Zhang; Kun Zhao

doi:10.1117/12.2637170

15 June 2022 Genetic algorithm based hyper-parameters optimization for transfer convolutional neural network

Chen Li, JinZhe Jiang, YaQian Zhao, RenGang Li, EnDong Wang, Xin Zhang, Kun Zhao

Proceedings Volume 12285, International Conference on Advanced Algorithms and Neural Networks (AANN 2022); 1228512 (2022) https://doi.org/10.1117/12.2637170
Event: International Conference on Advanced Algorithms and Neural Networks (AANN 2022), 2022, Zhuhai, China

Abstract

Hyperparameter optimization is a challenging problem in developing deep neural networks. Decision of transfer layers and trainable layers is a major task for design of the transfer convolutional neural networks (CNN). Conventional transfer CNN models are usually manually designed based on intuition. In this paper, a genetic algorithm is applied to select trainable layers of the transfer model. The filter criterion is constructed by accuracy and the counts of the trainable layers. The results show that the method is competent in this task. The system will converge with a precision of 97% in the classification of Cats and Dogs datasets, in no more than 15 generations. Moreover, backward inference according the results of the genetic algorithm shows that our method can capture the gradient features in network layers, which plays a part on understanding of the transfer AI models.

Citation Download Citation

Chen Li, JinZhe Jiang, YaQian Zhao, RenGang Li, EnDong Wang, Xin Zhang, and Kun Zhao "Genetic algorithm based hyper-parameters optimization for transfer convolutional neural network", Proc. SPIE 12285, International Conference on Advanced Algorithms and Neural Networks (AANN 2022), 1228512 (15 June 2022); https://doi.org/10.1117/12.2637170

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available