@article{ART002789903},
author={LEEJONGLAK},
title={Unification of Deep Learning Model trained by Parallel Learning in Security environment},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2021},
volume={26},
number={12},
pages={69-75},
doi={10.9708/jksci.2021.26.12.069}
TY - JOUR
AU - LEEJONGLAK
TI - Unification of Deep Learning Model trained by Parallel Learning in Security environment
JO - Journal of The Korea Society of Computer and Information
PY - 2021
VL - 26
IS - 12
PB - The Korean Society Of Computer And Information
SP - 69
EP - 75
SN - 1598-849X
AB - Recently, deep learning, which is the most used in the field of artificial intelligence, has a structure that is gradually becoming larger and more complex. As the deep learning model grows, a large amount of data is required to learn it, but there are cases in which it is difficult to integrate and learn the data because the data is distributed among several owners and security issues. In that situation we conducted parallel learning for each users that own data and then studied how to integrate it. For this, distributed learning was performed for each owner assuming the security situation as V-environment and H-environment, and the results of distributed learning were integrated using Average, Max, and AbsMax. As a result of applying this to the mnist-fashion data, it was confirmed that there was no significant difference from the results obtained by integrating the data in the V-environment in terms of accuracy. In the H-environment, although there was a difference, meaningful results were obtained.
KW - Security;Distributed Learning;Data Parallel;Deep Learning
DO - 10.9708/jksci.2021.26.12.069
ER -
LEEJONGLAK. (2021). Unification of Deep Learning Model trained by Parallel Learning in Security environment. Journal of The Korea Society of Computer and Information, 26(12), 69-75.
LEEJONGLAK. 2021, "Unification of Deep Learning Model trained by Parallel Learning in Security environment", Journal of The Korea Society of Computer and Information, vol.26, no.12 pp.69-75. Available from: doi:10.9708/jksci.2021.26.12.069
LEEJONGLAK "Unification of Deep Learning Model trained by Parallel Learning in Security environment" Journal of The Korea Society of Computer and Information 26.12 pp.69-75 (2021) : 69.
LEEJONGLAK. Unification of Deep Learning Model trained by Parallel Learning in Security environment. 2021; 26(12), 69-75. Available from: doi:10.9708/jksci.2021.26.12.069
LEEJONGLAK. "Unification of Deep Learning Model trained by Parallel Learning in Security environment" Journal of The Korea Society of Computer and Information 26, no.12 (2021) : 69-75.doi: 10.9708/jksci.2021.26.12.069
LEEJONGLAK. Unification of Deep Learning Model trained by Parallel Learning in Security environment. Journal of The Korea Society of Computer and Information, 26(12), 69-75. doi: 10.9708/jksci.2021.26.12.069
LEEJONGLAK. Unification of Deep Learning Model trained by Parallel Learning in Security environment. Journal of The Korea Society of Computer and Information. 2021; 26(12) 69-75. doi: 10.9708/jksci.2021.26.12.069
LEEJONGLAK. Unification of Deep Learning Model trained by Parallel Learning in Security environment. 2021; 26(12), 69-75. Available from: doi:10.9708/jksci.2021.26.12.069
LEEJONGLAK. "Unification of Deep Learning Model trained by Parallel Learning in Security environment" Journal of The Korea Society of Computer and Information 26, no.12 (2021) : 69-75.doi: 10.9708/jksci.2021.26.12.069