(A) low-power deep neural network online learning processor for real-time object tracking application = 실시간 객체 추적을 위한 저전력 심층 신경망 온라인 학습 프로세서

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 19
  • Download : 0
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
Advisors
Yoo, Hoi-Junresearcher유회준researcher
Description
한국과학기술원 :전기및전자공학부,
Publisher
한국과학기술원
Issue Date
2019
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2019.2,[1책 :]

Keywords

Deep neural network▼aonline learning▼aobject tracking▼afeedback alignment▼adropout; 심층신경망▼a온라인 학습▼a객체 추적▼a피드백 얼라인먼트▼a드롭아웃

URI
http://hdl.handle.net/10203/266860
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=843433&flag=dissertation
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0