DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Yoo, Hoi-Jun | - |
dc.contributor.advisor | 유회준 | - |
dc.contributor.author | Han, Donghyeon | - |
dc.date.accessioned | 2019-09-04T02:43:08Z | - |
dc.date.available | 2019-09-04T02:43:08Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=843433&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/266860 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2019.2,[1책 :] | - |
dc.description.abstract | A deep neural network (DNN) online learning processor is proposed with high throughput and low power consumption to achieve real-time object tracking in mobile devices. Four key features enable a low-power DNN online learning. First, a proposed processor is designed with a unified core architecture and it achieves 1.33 × higher throughput than the previous state-of-the-art DNN learning processor. Second, new algorithms, binary feedback alignment (BFA) and dynamic fixed-point based run-length compression (RLC), are proposed and reduce power consumption through the reduction of external memory accesses (EMA). Third, new data feeding units, including an integral RLC (iRLC) decoder and a transpose RLC (tRLC) decoder, are co-designed to maximize throughput alongside with the proposed algorithms. Finally, a dropout controller in this processor reduces redundant power consumption by the proposed dynamic clock-gating scheme. This enables the proposed processor to operate DNN online learning with 38.1% lower power consumption. Implemented with 65 nm CMOS technology, the 3.52$mm^2$ DNN online learning processor shows 126 mW power consumption and the processor achieves 30.4 frames-per-second (FPS) throughput in the object tracking application | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Deep neural network▼aonline learning▼aobject tracking▼afeedback alignment▼adropout | - |
dc.subject | 심층신경망▼a온라인 학습▼a객체 추적▼a피드백 얼라인먼트▼a드롭아웃 | - |
dc.title | (A) low-power deep neural network online learning processor for real-time object tracking application | - |
dc.title.alternative | 실시간 객체 추적을 위한 저전력 심층 신경망 온라인 학습 프로세서 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 한동현 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.