Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Improved recurrent generative adversarial networks with regularization techniques and a controllable framework

Authors
Lee, MinhyeokTae, DonghyunChoi, Jae HunJung, Ho-YoulSeok, Junhee
Issue Date
10월-2020
Publisher
ELSEVIER SCIENCE INC
Keywords
Generative adversarial network; Recurrent neural network; Long short-term memory; Sample generation; Spectral normalization
Citation
INFORMATION SCIENCES, v.538, pp.428 - 443
Indexed
SCIE
SCOPUS
Journal Title
INFORMATION SCIENCES
Volume
538
Start Page
428
End Page
443
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/53053
DOI
10.1016/j.ins.2020.05.116
ISSN
0020-0255
Abstract
Generative Adversarial Network (GAN), a deep learning framework to generate synthetic but realistic samples, has produced astonishing results for image synthesis. However, because GAN is routinely used for image datasets, regularization methods for GAN have been developed for convolutional layers. In this study, to expand these methods for time-series data, which are one of the most common data types in various real datasets, modified regularization methods are proposed for Long Short-Term Memory (LSTM)based GANs. Specifically, the spectral normalization, hinge loss, orthogonal regularization, and the truncation trick are modified and assessed for LSTM-based GANs. Furthermore, a conditional GAN architecture called Controllable GAN (ControlGAN) is applied to LSTM-based GANs to produce the desired samples. The evaluations are conducted with sine wave data, air pollution datasets, and a medical time-series dataset obtained from intensive care units. As a result, ControlGAN with the spectral normalization on gates and cell states consistently outperforms the others, including the conventional model, called Recurrent Conditional GAN (RCGAN). (C) 2020 Elsevier Inc. All rights reserved.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > School of Electrical Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher SEOK, Jun hee photo

SEOK, Jun hee
공과대학 (전기전자공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE