Improved recurrent generative adversarial networks with regularization techniques and a controllable framework
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Minhyeok | - |
dc.contributor.author | Tae, Donghyun | - |
dc.contributor.author | Choi, Jae Hun | - |
dc.contributor.author | Jung, Ho-Youl | - |
dc.contributor.author | Seok, Junhee | - |
dc.date.accessioned | 2021-08-30T13:52:23Z | - |
dc.date.available | 2021-08-30T13:52:23Z | - |
dc.date.created | 2021-06-18 | - |
dc.date.issued | 2020-10 | - |
dc.identifier.issn | 0020-0255 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/53053 | - |
dc.description.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. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER SCIENCE INC | - |
dc.title | Improved recurrent generative adversarial networks with regularization techniques and a controllable framework | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Seok, Junhee | - |
dc.identifier.doi | 10.1016/j.ins.2020.05.116 | - |
dc.identifier.scopusid | 2-s2.0-85086887200 | - |
dc.identifier.wosid | 000600348500008 | - |
dc.identifier.bibliographicCitation | INFORMATION SCIENCES, v.538, pp.428 - 443 | - |
dc.relation.isPartOf | INFORMATION SCIENCES | - |
dc.citation.title | INFORMATION SCIENCES | - |
dc.citation.volume | 538 | - |
dc.citation.startPage | 428 | - |
dc.citation.endPage | 443 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.subject.keywordAuthor | Generative adversarial network | - |
dc.subject.keywordAuthor | Recurrent neural network | - |
dc.subject.keywordAuthor | Long short-term memory | - |
dc.subject.keywordAuthor | Sample generation | - |
dc.subject.keywordAuthor | Spectral normalization | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.