Co-design of DNN model optimization for binary ReRAM array in-memory processing

Yue Guan, Takashi Ohsawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this work, a novel design of ReRAM neuromorphic system is proposed to process deep neural network (DNN) fully in array efficiently. A binary neural network model is constructed and optimized on MNIST dataset. The obtained model is simulated to be processed with the proposed ReRAM array. Co-design between hardware and network model optimization in software is analyzed to achieve feasible hardware design and generalizable model. Deployed with such co-design model, ReRAM array processes DNN with high robustness against fabrication fluctuation.

Original languageEnglish
Title of host publication2019 IEEE 11th International Memory Workshop, IMW 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728109817
DOIs
Publication statusPublished - 2019 May 1
Event11th IEEE International Memory Workshop, IMW 2019 - Montterey, United States
Duration: 2019 May 122019 May 15

Publication series

Name2019 IEEE 11th International Memory Workshop, IMW 2019

Conference

Conference11th IEEE International Memory Workshop, IMW 2019
CountryUnited States
CityMontterey
Period19/5/1219/5/15

Fingerprint

Data storage equipment
Processing
Hardware
RRAM
Deep neural networks
Neural networks
Fabrication

Keywords

  • binary neural network
  • fabrication fluctuation
  • neuromorphic ReRAM

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Guan, Y., & Ohsawa, T. (2019). Co-design of DNN model optimization for binary ReRAM array in-memory processing. In 2019 IEEE 11th International Memory Workshop, IMW 2019 [8739722] (2019 IEEE 11th International Memory Workshop, IMW 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IMW.2019.8739722

Co-design of DNN model optimization for binary ReRAM array in-memory processing. / Guan, Yue; Ohsawa, Takashi.

2019 IEEE 11th International Memory Workshop, IMW 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8739722 (2019 IEEE 11th International Memory Workshop, IMW 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Guan, Y & Ohsawa, T 2019, Co-design of DNN model optimization for binary ReRAM array in-memory processing. in 2019 IEEE 11th International Memory Workshop, IMW 2019., 8739722, 2019 IEEE 11th International Memory Workshop, IMW 2019, Institute of Electrical and Electronics Engineers Inc., 11th IEEE International Memory Workshop, IMW 2019, Montterey, United States, 19/5/12. https://doi.org/10.1109/IMW.2019.8739722
Guan Y, Ohsawa T. Co-design of DNN model optimization for binary ReRAM array in-memory processing. In 2019 IEEE 11th International Memory Workshop, IMW 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8739722. (2019 IEEE 11th International Memory Workshop, IMW 2019). https://doi.org/10.1109/IMW.2019.8739722
Guan, Yue ; Ohsawa, Takashi. / Co-design of DNN model optimization for binary ReRAM array in-memory processing. 2019 IEEE 11th International Memory Workshop, IMW 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 IEEE 11th International Memory Workshop, IMW 2019).
@inproceedings{2e637885bd9a40e0b725bd72e95e52d8,
title = "Co-design of DNN model optimization for binary ReRAM array in-memory processing",
abstract = "In this work, a novel design of ReRAM neuromorphic system is proposed to process deep neural network (DNN) fully in array efficiently. A binary neural network model is constructed and optimized on MNIST dataset. The obtained model is simulated to be processed with the proposed ReRAM array. Co-design between hardware and network model optimization in software is analyzed to achieve feasible hardware design and generalizable model. Deployed with such co-design model, ReRAM array processes DNN with high robustness against fabrication fluctuation.",
keywords = "binary neural network, fabrication fluctuation, neuromorphic ReRAM",
author = "Yue Guan and Takashi Ohsawa",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/IMW.2019.8739722",
language = "English",
series = "2019 IEEE 11th International Memory Workshop, IMW 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE 11th International Memory Workshop, IMW 2019",

}

TY - GEN

T1 - Co-design of DNN model optimization for binary ReRAM array in-memory processing

AU - Guan, Yue

AU - Ohsawa, Takashi

PY - 2019/5/1

Y1 - 2019/5/1

N2 - In this work, a novel design of ReRAM neuromorphic system is proposed to process deep neural network (DNN) fully in array efficiently. A binary neural network model is constructed and optimized on MNIST dataset. The obtained model is simulated to be processed with the proposed ReRAM array. Co-design between hardware and network model optimization in software is analyzed to achieve feasible hardware design and generalizable model. Deployed with such co-design model, ReRAM array processes DNN with high robustness against fabrication fluctuation.

AB - In this work, a novel design of ReRAM neuromorphic system is proposed to process deep neural network (DNN) fully in array efficiently. A binary neural network model is constructed and optimized on MNIST dataset. The obtained model is simulated to be processed with the proposed ReRAM array. Co-design between hardware and network model optimization in software is analyzed to achieve feasible hardware design and generalizable model. Deployed with such co-design model, ReRAM array processes DNN with high robustness against fabrication fluctuation.

KW - binary neural network

KW - fabrication fluctuation

KW - neuromorphic ReRAM

UR - http://www.scopus.com/inward/record.url?scp=85068349191&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068349191&partnerID=8YFLogxK

U2 - 10.1109/IMW.2019.8739722

DO - 10.1109/IMW.2019.8739722

M3 - Conference contribution

AN - SCOPUS:85068349191

T3 - 2019 IEEE 11th International Memory Workshop, IMW 2019

BT - 2019 IEEE 11th International Memory Workshop, IMW 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -