Rapid neural architecture search by learning to generate graphs from datasets데이터 세트 기반 그래프 생성을 통한 매우 빠른 인공신경망 탐색법

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 175
  • Download : 0
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.
Advisors
Hwang, Sung Juresearcher황성주researcher
Description
한국과학기술원 :AI대학원,
Publisher
한국과학기술원
Issue Date
2021
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : AI대학원, 2021.8,[iv, 24 p. :]

Keywords

Artificial Intelligence▼aMachine Learning▼aDeep Learning▼aMeta Learning▼aNeural Architecture Search; 인공지능▼a머신러닝▼a딥러닝▼a메타러닝▼a인공신경망 탐색

URI
http://hdl.handle.net/10203/294851
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=963750&flag=dissertation
Appears in Collection
AI-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0