DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Park, Dong-Jo | - |
dc.contributor.advisor | 박동조 | - |
dc.contributor.author | Kim, Jeong-Hoon | - |
dc.contributor.author | 김정훈 | - |
dc.date.accessioned | 2011-12-14T02:10:53Z | - |
dc.date.available | 2011-12-14T02:10:53Z | - |
dc.date.issued | 1992 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=59716&flag=dissertation | - |
dc.identifier.uri | http://hdl.handle.net/10203/38909 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기 및 전자공학과, 1992.2, [ iii, 51 p. ] | - |
dc.description.abstract | A fast learning algorithm for a multi layer feedforward neural network is proposed in this thesis. The proposed learning algorithm, based on an innovative variable step size and gradient averaging, has excellent properties to overcome major drawbacks of backpropagation algorithm and shows fast convergence speed. Also in this thesis, a new non-linear echo canceller, combined linear-nonlinear transversal filter, using the multi layer perceptron and the linear adaptive filter is proposed. This new echo canceller shows fast convergence speed than other non-linear echo canceller and achieves desired cancellation of echo required for digital data transmission. | eng |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.title | Multi layer neural networks for adaptive filtering applications | - |
dc.title.alternative | 다층 구조 신경회로망의 적응 필터링에의 응용에 대한 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 59716/325007 | - |
dc.description.department | 한국과학기술원 : 전기 및 전자공학과, | - |
dc.identifier.uid | 000901110 | - |
dc.contributor.localauthor | Park, Dong-Jo | - |
dc.contributor.localauthor | 박동조 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.