DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Bae, Hyeonmin | - |
dc.contributor.advisor | 배현민 | - |
dc.contributor.author | Lee, Jaewon | - |
dc.date.accessioned | 2022-04-27T19:31:19Z | - |
dc.date.available | 2022-04-27T19:31:19Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948738&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/295999 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2021.2,[v, 27p. :] | - |
dc.description.abstract | We suggested the FFT-based CNN accelerator to reduce the number of multiplication of the spatial-domain convolution. However, the precision of multiplication increases in spectral-domain convolution as much as the processing-gain of the FFT. Thus, the property of the image in the spectral-domain is used to reduce precision. The energy consumed by convolution operation is saved with the minimal penalty of classification accuracy. Also, the wireline communication bottleneck the energy of the acceleration system. We investigated the reduced bit-error-rate requirement for wireline interface with significant energy-saving and negligible accuracy-loss. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | CNN▼aaccelerator▼aFFT▼aapproximate computing▼awireline communication | - |
dc.subject | 합성곱 신경망▼a가속기▼a고속 퓨리에 변환▼a근사 컴퓨팅▼a유선 통신 | - |
dc.title | Energy-efficient FFT-based CNN accelerator through approximate computing | - |
dc.title.alternative | 근사 컴퓨팅을 통한 고효율의 고속 퓨리에 변환 기반 합성곱 신경망 가속기 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 이재원 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.