Fuse Devices for Pruning in Memristive Neural Network

Kim, Tae-Hyeon; Hong, Kyungho; Kim, Sungjoon; Park, Jinwoo; Youn, Sangwook; Lee, Jong-Ho; Park, Byung-Gook; Kim, Hyungjin; Choi, Woo Young

doi:10.1109/LED.2023.3237651

상세 보기

Fuse Devices for Pruning in Memristive Neural Network

Kim, Tae-Hyeon;
Hong, Kyungho;
Kim, Sungjoon;
Park, Jinwoo;
Youn, Sangwook;
외 4명

Citations

WEB OF SCIENCE

5

Citations

SCOPUS

5

초록

In this study, we developed a fuse device for pruning implementation in a hardware neural network. A line-shaped fuse device was fabricated with aluminum metal and characterized in a one fuse and one resistive random-access memory (1F1R) structure. A blow time of 0.4 mu s and read endurance of >10(7) were achieved, and the cut-off operation of the fuse was successfully verified in 1F1R. In addition, we developed a fuse design method for blow voltage and current via adjustment of the length, width, and thickness of the fuse. The adjustments were adopted to utilize the fuse in various synaptic devices. Finally, using simulations, we demonstrated a performance improvement due to the network pruning wherein the defective devices are disconnected by the fuse operations.

키워드

Fuses; Resistance; Performance evaluation; Neural networks; Scanning electron microscopy; Neuromorphics; Microscopy; Fuse device; hardware neural network; network pruning; neuromorphic system; synaptic device; SYNAPSE DEVICE; MEMORY; TRANSISTORS; ARRAY; RRAM

제목: Fuse Devices for Pruning in Memristive Neural Network

저자: Kim, Tae-Hyeon; Hong, Kyungho; Kim, Sungjoon; Park, Jinwoo; Youn, Sangwook; Lee, Jong-Ho; Park, Byung-Gook; Kim, Hyungjin; Choi, Woo Young

DOI: 10.1109/LED.2023.3237651

발행일: 2023-03

유형: Article

저널명: IEEE Electron Device Letters

권: 44

호: 3

페이지: 520 ~ 523