DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Choi, Edward | - |
dc.contributor.advisor | 최윤재 | - |
dc.contributor.author | Lee, Jiyoung | - |
dc.date.accessioned | 2023-06-22T19:31:25Z | - |
dc.date.available | 2023-06-22T19:31:25Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1008208&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/308220 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2022.8,[iii, 15 p. :] | - |
dc.description.abstract | Periodic signals play an important role in daily lives. Although conventional sequential models have shown remarkable success in various fields, they still come short in modeling periodicity | - |
dc.description.abstract | they either collapse, diverge or ignore details. In this paper, we introduce a novel framework inspired by Fourier series to generate periodic signals. We first decompose the given signals into multiple sines and cosines and then conditionally generate periodic signals with the output components. We have shown our model efficacy on three tasks: reconstruction, imputation and conditional generation. Our model outperforms baselines in all tasks and shows more stable and refined results. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Conditional generative model▼aPeriodic signals▼aFourier series | - |
dc.subject | 조건부 합성 모델▼a주기 신호▼a푸리에 시리즈 | - |
dc.title | Conditional generation of periodic signals with Fourier-based decoder | - |
dc.title.alternative | 푸리에 디코더를 통한 조건부 신호 합성 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | 이지영 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.