Share Email Print

Proceedings Paper

Training time reduction for network architecture search using genetic algorithm
Author(s): Yuki Matsuoka; Hiroaki Aizawa; Junya Sato; Kunihito Kato
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 16 July 2019
PDF: 7 pages
Proc. SPIE 11172, Fourteenth International Conference on Quality Control by Artificial Vision, 111720O (16 July 2019); doi: 10.1117/12.2521754
Show Author Affiliations
Yuki Matsuoka, Gifu Univ. (Japan)
Hiroaki Aizawa, Gifu Univ. (Japan)
Junya Sato, Gifu Univ. (Japan)
Kunihito Kato, Gifu Univ. (Japan)

Published in SPIE Proceedings Vol. 11172:
Fourteenth International Conference on Quality Control by Artificial Vision
Christophe Cudel; Stéphane Bazeille; Nicolas Verrier, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?