BROWSE

ITEM VIEW & DOWNLOAD

Architecture-accuracy co-optimization of reram-based low-cost neural network processor

Cited 0 times inthomson ciCited 0 times inthomson ci
Title
Architecture-accuracy co-optimization of reram-based low-cost neural network processor
Author
LEE, Se-Gi
Advisor
Lee, Jong-Eun
Keywords
Deep learning; AI; Neuromorphic; ReRAM; crossbar array
Issue Date
2020-08
Publisher
Graduate School of UNIST
Abstract
Resistive RAM (ReRAM) is a promising technology with such advantages as small device size and in-memory-computing capability. However, designing optimal AI processors based on ReRAMs is challenging due to the limited precision, and the complex interplay between quality of result and hardware efficiency. In this paper we present a study targeting a low-power low-cost image classification application. We discover that the trade-off between accuracy and hardware efficiency in ReRAM-based hardware is not obvious and even surprising, and our solution developed for a recently fabricated ReRAM device achieves both the state-of-the-art efficiency and empirical assurance on the high quality of result.
Description
Department of Electrical Engineering
URI
Go to Link
Appears in Collections:
EE_Theses_Master
Files in This Item:
Architecture-accuracy co-optimization of reram-based low-cost neural network processor.pdf Download

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show full item record

qrcode

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

MENU