DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Hwang, Sung Ju | - |
dc.contributor.advisor | 황성주 | - |
dc.contributor.author | Hyung, Eunyoung | - |
dc.date.accessioned | 2022-04-15T07:56:34Z | - |
dc.date.available | 2022-04-15T07:56:34Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=963750&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/294851 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : AI대학원, 2021.8,[iv, 24 p. :] | - |
dc.description.abstract | Despite the success of recent Neural Architecture Search (NAS) methods on various tasks which have shown to output networks that largely outperform human-designed networks, conventional NAS methods have mostly tackled the optimization of searching for the network architecture for a single task (dataset), which does not generalize well across multiple tasks (datasets). Moreover, since such task-specific methods search for a neural architecture from scratch for every given task, they incur a large computational cost, which is problematic when the time and monetary budget are limited. In this paper, we propose an efficient NAS framework that is trained once on a database consisting of datasets and pretrained networks and can rapidly search for a neural architecture for a novel dataset. The proposed MetaD2A (Meta Dataset-to-Architecture) model can stochastically generate graphs (architectures) from a given set (dataset) via a cross-modal latent space learned with amortized meta-learning. Moreover, we also propose a meta-performance predictor to estimate and select the best architecture without direct training on target datasets. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Artificial Intelligence▼aMachine Learning▼aDeep Learning▼aMeta Learning▼aNeural Architecture Search | - |
dc.subject | 인공지능▼a머신러닝▼a딥러닝▼a메타러닝▼a인공신경망 탐색 | - |
dc.title | Rapid neural architecture search by learning to generate graphs from datasets | - |
dc.title.alternative | 데이터 세트 기반 그래프 생성을 통한 매우 빠른 인공신경망 탐색법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :AI대학원, | - |
dc.contributor.alternativeauthor | 형은영 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.