In-place zero-space memory protection for CNN

Hui Guan; Lin Ning; Zhen Lin; Xipeng Shen; Huiyang Zhou; Seung Hwan Lim

In-place zero-space memory protection for CNN

Hui Guan, Lin Ning, Zhen Lin, Xipeng Shen, Huiyang Zhou, Seung Hwan Lim

Discrete Algorithms

North Carolina State University

Research output: Contribution to journal › Conference article › peer-review

15 Scopus citations

Abstract

Convolutional Neural Networks (CNN) are being actively explored for safety-critical applications such as autonomous vehicles and aerospace, where it is essential to ensure the reliability of inference results in the presence of possible memory faults. Traditional methods such as error correction codes (ECC) and Triple Modular Redundancy (TMR) are CNN-oblivious and incur substantial memory overhead and energy cost. This paper introduces in-place zero-space ECC assisted with a new training scheme weight distribution-oriented training. The new method provides the first known zero space cost memory protection for CNNs without compromising the reliability offered by traditional ECC.

Original language	English
Journal	Advances in Neural Information Processing Systems
Volume	32
State	Published - 2019
Event	33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019 - Vancouver, Canada Duration: Dec 8 2019 → Dec 14 2019

Bibliographical note

Publisher Copyright:
© 2019 Neural information processing systems foundation. All rights reserved.

Cite this

@article{907052262c4347a0aab0c4a520b4cc00,

title = "In-place zero-space memory protection for CNN",

abstract = "Convolutional Neural Networks (CNN) are being actively explored for safety-critical applications such as autonomous vehicles and aerospace, where it is essential to ensure the reliability of inference results in the presence of possible memory faults. Traditional methods such as error correction codes (ECC) and Triple Modular Redundancy (TMR) are CNN-oblivious and incur substantial memory overhead and energy cost. This paper introduces in-place zero-space ECC assisted with a new training scheme weight distribution-oriented training. The new method provides the first known zero space cost memory protection for CNNs without compromising the reliability offered by traditional ECC.",

author = "Hui Guan and Lin Ning and Zhen Lin and Xipeng Shen and Huiyang Zhou and Lim, {Seung Hwan}",

note = "Publisher Copyright: {\textcopyright} 2019 Neural information processing systems foundation. All rights reserved.; 33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019 ; Conference date: 08-12-2019 Through 14-12-2019",

year = "2019",

language = "English",

volume = "32",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

}

TY - JOUR

T1 - In-place zero-space memory protection for CNN

AU - Guan, Hui

AU - Ning, Lin

AU - Lin, Zhen

AU - Shen, Xipeng

AU - Zhou, Huiyang

AU - Lim, Seung Hwan

PY - 2019

Y1 - 2019

N2 - Convolutional Neural Networks (CNN) are being actively explored for safety-critical applications such as autonomous vehicles and aerospace, where it is essential to ensure the reliability of inference results in the presence of possible memory faults. Traditional methods such as error correction codes (ECC) and Triple Modular Redundancy (TMR) are CNN-oblivious and incur substantial memory overhead and energy cost. This paper introduces in-place zero-space ECC assisted with a new training scheme weight distribution-oriented training. The new method provides the first known zero space cost memory protection for CNNs without compromising the reliability offered by traditional ECC.

AB - Convolutional Neural Networks (CNN) are being actively explored for safety-critical applications such as autonomous vehicles and aerospace, where it is essential to ensure the reliability of inference results in the presence of possible memory faults. Traditional methods such as error correction codes (ECC) and Triple Modular Redundancy (TMR) are CNN-oblivious and incur substantial memory overhead and energy cost. This paper introduces in-place zero-space ECC assisted with a new training scheme weight distribution-oriented training. The new method provides the first known zero space cost memory protection for CNNs without compromising the reliability offered by traditional ECC.

UR - http://www.scopus.com/inward/record.url?scp=85090172995&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85090172995

SN - 1049-5258

VL - 32

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

T2 - 33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019

Y2 - 8 December 2019 through 14 December 2019

ER -

In-place zero-space memory protection for CNN

Abstract

Bibliographical note

Other files and links

Fingerprint

Cite this