DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Chong, Song | - |
dc.contributor.advisor | 정송 | - |
dc.contributor.author | Lee, Sewoong | - |
dc.date.accessioned | 2019-09-04T02:44:18Z | - |
dc.date.available | 2019-09-04T02:44:18Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=843412&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/266921 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2019.2,[iii, 18 p. :] | - |
dc.description.abstract | For an artificial neural network to perform well, it is necessary to design an appropriate internal hierarchy, which requires a lot of time and expertise. Therefore, a method to automate the neural network structure design has been proposed, and a structure that can perform better than the human structure has been found. However, this method has a problem that takes a vast computational resource, because of huge search space and repetitive training. In this thesis, we propose a method to search the neural network efficiently by constructing the search range systematically through network transformation and Bayesian optimization method. Our method can finds a better convolution neural network architecture than the other methods under limited number of network evaluation conditions. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Convolutional neural network▼aneural architecture search▼abayesian optimization▼anetwork transformation▼adeep learning | - |
dc.subject | 컨볼루젼 신경망▼a신경망 구조 탐색▼a베이지안 최적화▼a네트워크 변형▼a딥 러닝 | - |
dc.title | Neural architecture search with bayesian optimization and network transformation | - |
dc.title.alternative | 베이지안 최적화 및 네트워크 변형을 이용한 신경망 구조 탐색 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 이세웅 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.