Early Image Termination Technique during STDP Training of Spiking Neural Network

Dongwoo Lew; Jongsun Park

doi:10.1109/ISOCC50952.2020.9333081

Early Image Termination Technique during STDP Training of Spiking Neural Network

Dongwoo Lew, Jongsun Park

School of Electrical Engineering

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

1 Citation (Scopus)

Abstract

Spiking Neural Network (SNN) is a breed of neural networks that seek to achieve low energy and power by more closely mimicking biological brains. SNNs are often trained using lightweight unsupervised learning such as Spike Time Dependent Plasticity (STDP). However, STDP is prone to redundant time steps during training since STDP cannot determine current image needs further training or not. To reduce redundant time steps and lower energy costs during STDP training, we propose a novel technique that terminates training upon an image preemptively. The proposed technique reduces time steps by 44% with accuracy drop of 0.91% on MNIST.

Original language	English
Title of host publication	Proceedings - International SoC Design Conference, ISOCC 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	79-80
Number of pages	2
ISBN (Electronic)	9781728183312
DOIs	https://doi.org/10.1109/ISOCC50952.2020.9333081
Publication status	Published - 2020 Oct 21
Event	17th International System-on-Chip Design Conference, ISOCC 2020 - Yeosu, Korea, Republic of Duration: 2020 Oct 21 → 2020 Oct 24

Publication series

Name	Proceedings - International SoC Design Conference, ISOCC 2020

Conference

Conference	17th International System-on-Chip Design Conference, ISOCC 2020
Country/Territory	Korea, Republic of
City	Yeosu
Period	20/10/21 → 20/10/24

Bibliographical note

Funding Information:
This work was supported by the Industrial Strategic Technology Development Program(10077445, Development of SoC technology based on Spiking Neural Cell for smart mobile and IoT Devices) funded By the Ministry of Trade, Industry & Energy(MOTIE, Korea)

Publisher Copyright:
© 2020 IEEE.

Keywords

Spike Timing Dependant Plasticity (STDP)
Spking Neural Network (SNN)

ASJC Scopus subject areas

Energy Engineering and Power Technology
Electrical and Electronic Engineering
Instrumentation
Artificial Intelligence
Hardware and Architecture

Access to Document

10.1109/ISOCC50952.2020.9333081

Cite this

Lew, D., & Park, J. (2020). Early Image Termination Technique during STDP Training of Spiking Neural Network. In Proceedings - International SoC Design Conference, ISOCC 2020 (pp. 79-80). Article 9333081 (Proceedings - International SoC Design Conference, ISOCC 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISOCC50952.2020.9333081

Early Image Termination Technique during STDP Training of Spiking Neural Network. / Lew, Dongwoo; Park, Jongsun.
Proceedings - International SoC Design Conference, ISOCC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 79-80 9333081 (Proceedings - International SoC Design Conference, ISOCC 2020).

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

Lew, D & Park, J 2020, Early Image Termination Technique during STDP Training of Spiking Neural Network. in Proceedings - International SoC Design Conference, ISOCC 2020., 9333081, Proceedings - International SoC Design Conference, ISOCC 2020, Institute of Electrical and Electronics Engineers Inc., pp. 79-80, 17th International System-on-Chip Design Conference, ISOCC 2020, Yeosu, Korea, Republic of, 20/10/21. https://doi.org/10.1109/ISOCC50952.2020.9333081

@inproceedings{4c3676eee29e480e832060670a116a37,

title = "Early Image Termination Technique during STDP Training of Spiking Neural Network",

abstract = "Spiking Neural Network (SNN) is a breed of neural networks that seek to achieve low energy and power by more closely mimicking biological brains. SNNs are often trained using lightweight unsupervised learning such as Spike Time Dependent Plasticity (STDP). However, STDP is prone to redundant time steps during training since STDP cannot determine current image needs further training or not. To reduce redundant time steps and lower energy costs during STDP training, we propose a novel technique that terminates training upon an image preemptively. The proposed technique reduces time steps by 44% with accuracy drop of 0.91% on MNIST. ",

keywords = "Spike Timing Dependant Plasticity (STDP), Spking Neural Network (SNN)",

author = "Dongwoo Lew and Jongsun Park",

note = "Funding Information: This work was supported by the Industrial Strategic Technology Development Program(10077445, Development of SoC technology based on Spiking Neural Cell for smart mobile and IoT Devices) funded By the Ministry of Trade, Industry & Energy(MOTIE, Korea) Publisher Copyright: {\textcopyright} 2020 IEEE.; 17th International System-on-Chip Design Conference, ISOCC 2020 ; Conference date: 21-10-2020 Through 24-10-2020",

year = "2020",

month = oct,

day = "21",

doi = "10.1109/ISOCC50952.2020.9333081",

language = "English",

series = "Proceedings - International SoC Design Conference, ISOCC 2020",

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

pages = "79--80",

booktitle = "Proceedings - International SoC Design Conference, ISOCC 2020",

}

TY - GEN

T1 - Early Image Termination Technique during STDP Training of Spiking Neural Network

AU - Lew, Dongwoo

AU - Park, Jongsun

N1 - Funding Information: This work was supported by the Industrial Strategic Technology Development Program(10077445, Development of SoC technology based on Spiking Neural Cell for smart mobile and IoT Devices) funded By the Ministry of Trade, Industry & Energy(MOTIE, Korea) Publisher Copyright: © 2020 IEEE.

PY - 2020/10/21

Y1 - 2020/10/21

N2 - Spiking Neural Network (SNN) is a breed of neural networks that seek to achieve low energy and power by more closely mimicking biological brains. SNNs are often trained using lightweight unsupervised learning such as Spike Time Dependent Plasticity (STDP). However, STDP is prone to redundant time steps during training since STDP cannot determine current image needs further training or not. To reduce redundant time steps and lower energy costs during STDP training, we propose a novel technique that terminates training upon an image preemptively. The proposed technique reduces time steps by 44% with accuracy drop of 0.91% on MNIST.

AB - Spiking Neural Network (SNN) is a breed of neural networks that seek to achieve low energy and power by more closely mimicking biological brains. SNNs are often trained using lightweight unsupervised learning such as Spike Time Dependent Plasticity (STDP). However, STDP is prone to redundant time steps during training since STDP cannot determine current image needs further training or not. To reduce redundant time steps and lower energy costs during STDP training, we propose a novel technique that terminates training upon an image preemptively. The proposed technique reduces time steps by 44% with accuracy drop of 0.91% on MNIST.

KW - Spike Timing Dependant Plasticity (STDP)

KW - Spking Neural Network (SNN)

UR - http://www.scopus.com/inward/record.url?scp=85100807956&partnerID=8YFLogxK

U2 - 10.1109/ISOCC50952.2020.9333081

DO - 10.1109/ISOCC50952.2020.9333081

M3 - Conference contribution

AN - SCOPUS:85100807956

T3 - Proceedings - International SoC Design Conference, ISOCC 2020

SP - 79

EP - 80

BT - Proceedings - International SoC Design Conference, ISOCC 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th International System-on-Chip Design Conference, ISOCC 2020

Y2 - 21 October 2020 through 24 October 2020

ER -

Early Image Termination Technique during STDP Training of Spiking Neural Network

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this