The 9th International Conference on Next Generation Computing 2023 (2023.12)바로가기
페이지
pp.27-28
저자
Jeahack Lee, Hyeonseong Kim, Junwon Jeong, Kyeongmook Oh, Byung-Soo Kim
언어
영어(ENG)
URL
https://www.earticle.net/Article/A448107
원문정보
초록
영어
This paper proposes a binarized neural network (BNN) processor supporting residual networks. The processor was fabricated in UMC 40-nm CMOS technology. Test results show that performance and energy efficiency are 1036.8 GOPS, and 66.5 GOPS/mW at 200MHz, respectively.
목차
Abstract I. INTRODUCTION II. PROPOSED BINARIZED RESNETE DATA FLOW III. PROPOSED BNN ARCHITECTURE IV. IMPLEMENTATION AND RESULTS V. CONCLUSION ACKNOWLEDGMENT REFERENCES