Training time reduction for network architecture search using genetic algorithm

Yuki Matsuoka; Hiroaki Aizawa; Junya Sato; Kunihito Kato

doi:10.1117/12.2521754

16 July 2019 Training time reduction for network architecture search using genetic algorithm

Yuki Matsuoka, Hiroaki Aizawa, Junya Sato, Kunihito Kato

Proceedings Volume 11172, Fourteenth International Conference on Quality Control by Artificial Vision; 111720O (2019) https://doi.org/10.1117/12.2521754
Event: Fourteenth International Conference on Quality Control by Artificial Vision, 2019, Mulhouse, France

Abstract

Designing the optimal architecture of neural networks is an important issue. However, since this is difficult even for experienced experts, automatic optimization of the network architecture is required. In this study, we regard this issue as a combinatorial optimization problem, and utilize genetic algorithm to optimize the network architecture. Because training the networks, which are represented by individuals in GA, takes a long time, a novel method to reduce the training time by inheriting the weights of the trained network is proposed. From experimental results, our proposed method achieved the time reduction and higher accuracy than a conventional method.

Citation Download Citation

Yuki Matsuoka, Hiroaki Aizawa, Junya Sato, and Kunihito Kato "Training time reduction for network architecture search using genetic algorithm", Proc. SPIE 11172, Fourteenth International Conference on Quality Control by Artificial Vision, 111720O (16 July 2019); https://doi.org/10.1117/12.2521754

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