DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Jong-Hwan | - |
dc.contributor.advisor | 김종환 | - |
dc.contributor.author | Myeong, Hyeon | - |
dc.contributor.author | 명현 | - |
dc.date.accessioned | 2011-12-14T01:59:35Z | - |
dc.date.available | 2011-12-14T01:59:35Z | - |
dc.date.issued | 1994 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=69394&flag=dissertation | - |
dc.identifier.uri | http://hdl.handle.net/10203/38174 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기 및 전자공학과, 1994.2, [ ii, 60 p. ] | - |
dc.description.abstract | A two-phase neural network solves exact feasible solutions when the problem is a constrained optimization programming. The time-varying programmming neural network is a kind of modified steepest-gradient algorithm which solves time-varying optimization problems. In this paper, a time-varying two-phase optimization neural network is proposed which uses the merits of the two-phase neural network and the time-varying neural network. The training of multi-layer neural networks is regarded as a time-varying optimization problem, and the proposed algorithm is applied to system identification or function learning and control using a multi-layer neural network. Furthermore, we considered the case where the weights have some constraints in the learning of the neural network. | eng |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.title | Time-varying two-phase optimization and its application to neural network learning | - |
dc.title.alternative | 시변 이상 최적화 및 이를 이용한 신경회로망의 학습 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 69394/325007 | - |
dc.description.department | 한국과학기술원 : 전기 및 전자공학과, | - |
dc.identifier.uid | 000923171 | - |
dc.contributor.localauthor | Kim, Jong-Hwan | - |
dc.contributor.localauthor | 김종환 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.