SENIN: An energy-efficient sparse neuromorphic system with on-chip learning

Myung Hoon Choi; Seungkyu Choi; Jaehyeong Sim; Lee Sup Kim

doi:10.1109/ISLPED.2017.8009174

SENIN: An energy-efficient sparse neuromorphic system with on-chip learning

Myung Hoon Choi, Seungkyu Choi, Jaehyeong Sim, Lee Sup Kim

Department of Computer Science & Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

Applying highly accurate neural networks to mobile devices encounters energy problems in battery-limited mobile environments. To resolve these problems, neuromorphic hardware solutions that enable event-driven operation have been proposed. In this work, we present a novel sparse neuromorphic system that implements an E-I Net algorithm to further improve energy efficiency. We introduce a neuron clock-gating technique that significantly reduces energy consumption by predicting future neuron spike activity without any loss of accuracy. We also propose synaptic pruning to save additional energy with minimal impact on classification accuracy. For fast adaptation to a changing environment, a learning algorithm is implemented in the proposed system. Compared to prior studies, our experimental results illustrate that the proposed system achieves 5.3×-11.4× energy efficiency improvement with comparable accuracy.

Original language	English
Title of host publication	ISLPED 2017 - IEEE/ACM International Symposium on Low Power Electronics and Design
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781509060238
DOIs	https://doi.org/10.1109/ISLPED.2017.8009174
State	Published - 11 Aug 2017
Event	22nd IEEE/ACM International Symposium on Low Power Electronics and Design, ISLPED 2017 - Taipei, Taiwan, Province of China Duration: 24 Jul 2017 → 26 Jul 2017

Publication series

Name	Proceedings of the International Symposium on Low Power Electronics and Design
ISSN (Print)	1533-4678

Conference

Conference	22nd IEEE/ACM International Symposium on Low Power Electronics and Design, ISLPED 2017
Country/Territory	Taiwan, Province of China
City	Taipei
Period	24/07/17 → 26/07/17

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIP) (NO. 2017R1A2B2009380) 978-1-5090-6023-8/17/$31.00 © 2017 IEEE

Publisher Copyright:
© 2017 IEEE.

Keywords

Neural Network
Neuromorphic Computing
Sparse Spike

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ISLPED.2017.8009174

Cite this

Choi, M. H., Choi, S., Sim, J., & Kim, L. S. (2017). SENIN: An energy-efficient sparse neuromorphic system with on-chip learning. In ISLPED 2017 - IEEE/ACM International Symposium on Low Power Electronics and Design Article 8009174 (Proceedings of the International Symposium on Low Power Electronics and Design). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISLPED.2017.8009174

@inproceedings{3ebd86a4af2c487e9be440676a7842ee,

title = "SENIN: An energy-efficient sparse neuromorphic system with on-chip learning",

abstract = "Applying highly accurate neural networks to mobile devices encounters energy problems in battery-limited mobile environments. To resolve these problems, neuromorphic hardware solutions that enable event-driven operation have been proposed. In this work, we present a novel sparse neuromorphic system that implements an E-I Net algorithm to further improve energy efficiency. We introduce a neuron clock-gating technique that significantly reduces energy consumption by predicting future neuron spike activity without any loss of accuracy. We also propose synaptic pruning to save additional energy with minimal impact on classification accuracy. For fast adaptation to a changing environment, a learning algorithm is implemented in the proposed system. Compared to prior studies, our experimental results illustrate that the proposed system achieves 5.3×-11.4× energy efficiency improvement with comparable accuracy.",

keywords = "Neural Network, Neuromorphic Computing, Sparse Spike",

author = "Choi, {Myung Hoon} and Seungkyu Choi and Jaehyeong Sim and Kim, {Lee Sup}",

note = "Funding Information: This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIP) (NO. 2017R1A2B2009380) 978-1-5090-6023-8/17/$31.00 {\textcopyright} 2017 IEEE Publisher Copyright: {\textcopyright} 2017 IEEE.; 22nd IEEE/ACM International Symposium on Low Power Electronics and Design, ISLPED 2017 ; Conference date: 24-07-2017 Through 26-07-2017",

year = "2017",

month = aug,

day = "11",

doi = "10.1109/ISLPED.2017.8009174",

language = "English",

series = "Proceedings of the International Symposium on Low Power Electronics and Design",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "ISLPED 2017 - IEEE/ACM International Symposium on Low Power Electronics and Design",

}

Choi, MH, Choi, S, Sim, J & Kim, LS 2017, SENIN: An energy-efficient sparse neuromorphic system with on-chip learning. in ISLPED 2017 - IEEE/ACM International Symposium on Low Power Electronics and Design., 8009174, Proceedings of the International Symposium on Low Power Electronics and Design, Institute of Electrical and Electronics Engineers Inc., 22nd IEEE/ACM International Symposium on Low Power Electronics and Design, ISLPED 2017, Taipei, Taiwan, Province of China, 24/07/17. https://doi.org/10.1109/ISLPED.2017.8009174

SENIN: An energy-efficient sparse neuromorphic system with on-chip learning. / Choi, Myung Hoon; Choi, Seungkyu; Sim, Jaehyeong et al.
ISLPED 2017 - IEEE/ACM International Symposium on Low Power Electronics and Design. Institute of Electrical and Electronics Engineers Inc., 2017. 8009174 (Proceedings of the International Symposium on Low Power Electronics and Design).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - SENIN

T2 - 22nd IEEE/ACM International Symposium on Low Power Electronics and Design, ISLPED 2017

AU - Choi, Myung Hoon

AU - Choi, Seungkyu

AU - Sim, Jaehyeong

AU - Kim, Lee Sup

N1 - Funding Information: This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIP) (NO. 2017R1A2B2009380) 978-1-5090-6023-8/17/$31.00 © 2017 IEEE Publisher Copyright: © 2017 IEEE.

PY - 2017/8/11

Y1 - 2017/8/11

N2 - Applying highly accurate neural networks to mobile devices encounters energy problems in battery-limited mobile environments. To resolve these problems, neuromorphic hardware solutions that enable event-driven operation have been proposed. In this work, we present a novel sparse neuromorphic system that implements an E-I Net algorithm to further improve energy efficiency. We introduce a neuron clock-gating technique that significantly reduces energy consumption by predicting future neuron spike activity without any loss of accuracy. We also propose synaptic pruning to save additional energy with minimal impact on classification accuracy. For fast adaptation to a changing environment, a learning algorithm is implemented in the proposed system. Compared to prior studies, our experimental results illustrate that the proposed system achieves 5.3×-11.4× energy efficiency improvement with comparable accuracy.

AB - Applying highly accurate neural networks to mobile devices encounters energy problems in battery-limited mobile environments. To resolve these problems, neuromorphic hardware solutions that enable event-driven operation have been proposed. In this work, we present a novel sparse neuromorphic system that implements an E-I Net algorithm to further improve energy efficiency. We introduce a neuron clock-gating technique that significantly reduces energy consumption by predicting future neuron spike activity without any loss of accuracy. We also propose synaptic pruning to save additional energy with minimal impact on classification accuracy. For fast adaptation to a changing environment, a learning algorithm is implemented in the proposed system. Compared to prior studies, our experimental results illustrate that the proposed system achieves 5.3×-11.4× energy efficiency improvement with comparable accuracy.

KW - Neural Network

KW - Neuromorphic Computing

KW - Sparse Spike

UR - http://www.scopus.com/inward/record.url?scp=85028613253&partnerID=8YFLogxK

U2 - 10.1109/ISLPED.2017.8009174

DO - 10.1109/ISLPED.2017.8009174

M3 - Conference contribution

AN - SCOPUS:85028613253

T3 - Proceedings of the International Symposium on Low Power Electronics and Design

BT - ISLPED 2017 - IEEE/ACM International Symposium on Low Power Electronics and Design

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 24 July 2017 through 26 July 2017

ER -

Choi MH, Choi S, Sim J, Kim LS. SENIN: An energy-efficient sparse neuromorphic system with on-chip learning. In ISLPED 2017 - IEEE/ACM International Symposium on Low Power Electronics and Design. Institute of Electrical and Electronics Engineers Inc. 2017. 8009174. (Proceedings of the International Symposium on Low Power Electronics and Design). doi: 10.1109/ISLPED.2017.8009174

SENIN: An energy-efficient sparse neuromorphic system with on-chip learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this