Interchangeable Hebbian and Anti-Hebbian STDP Applied to Supervised Learning in Spiking Neural Network

Che Chia Chang; Pin Chun Chen; Boris Hudec; Po-Tsun Liu; Tuo-Hung Hou

doi:10.1109/IEDM.2018.8614648

Interchangeable Hebbian and Anti-Hebbian STDP Applied to Supervised Learning in Spiking Neural Network

Che Chia Chang, Pin Chun Chen, Boris Hudec, Po-Tsun Liu, Tuo-Hung Hou

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

4 Scopus citations

Abstract

This work provides a complete framework, including device, architecture, and algorithm, for implementing bio-inspired supervised spiking neural networks (SNNs) on hardware. An analog synapse with atypical dual bipolar resistive-switching (D-BRS) modes demonstrates interchangeable Hebbian spiking-timing-dependent plasticity (STDP) and anti-Hebbian STDP, and it is capable of implementing supervised ReSuMe SNNs in crossbar arrays. By using an 'exchange' update scheme, accurate supervised learning (∼96% for MNIST) is achieved in a compact network.

Original language	English
Title of host publication	2018 IEEE International Electron Devices Meeting, IEDM 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	15.5.1-15.5.4
ISBN (Electronic)	9781728119878
DOIs	https://doi.org/10.1109/IEDM.2018.8614648
State	Published - 16 Jan 2019
Event	64th Annual IEEE International Electron Devices Meeting, IEDM 2018 - San Francisco, United States Duration: 1 Dec 2018 → 5 Dec 2018

Publication series

Name	Technical Digest - International Electron Devices Meeting, IEDM
Volume	2018-December
ISSN (Print)	0163-1918

Conference

Conference	64th Annual IEEE International Electron Devices Meeting, IEDM 2018
Country/Territory	United States
City	San Francisco
Period	1/12/18 → 5/12/18

Access to Document

10.1109/IEDM.2018.8614648

Cite this

Chang, C. C., Chen, P. C., Hudec, B., Liu, P-T., & Hou, T-H. (2019). Interchangeable Hebbian and Anti-Hebbian STDP Applied to Supervised Learning in Spiking Neural Network. In 2018 IEEE International Electron Devices Meeting, IEDM 2018 (pp. 15.5.1-15.5.4). [8614648] (Technical Digest - International Electron Devices Meeting, IEDM; Vol. 2018-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IEDM.2018.8614648

@inproceedings{d887ad16d3cb4335bf91c2f8996b4734,

title = "Interchangeable Hebbian and Anti-Hebbian STDP Applied to Supervised Learning in Spiking Neural Network",

abstract = "This work provides a complete framework, including device, architecture, and algorithm, for implementing bio-inspired supervised spiking neural networks (SNNs) on hardware. An analog synapse with atypical dual bipolar resistive-switching (D-BRS) modes demonstrates interchangeable Hebbian spiking-timing-dependent plasticity (STDP) and anti-Hebbian STDP, and it is capable of implementing supervised ReSuMe SNNs in crossbar arrays. By using an 'exchange' update scheme, accurate supervised learning (∼96% for MNIST) is achieved in a compact network.",

author = "Chang, {Che Chia} and Chen, {Pin Chun} and Boris Hudec and Po-Tsun Liu and Tuo-Hung Hou",

year = "2019",

month = jan,

day = "16",

doi = "10.1109/IEDM.2018.8614648",

language = "English",

series = "Technical Digest - International Electron Devices Meeting, IEDM",

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

pages = "15.5.1--15.5.4",

booktitle = "2018 IEEE International Electron Devices Meeting, IEDM 2018",

address = "United States",

note = "64th Annual IEEE International Electron Devices Meeting, IEDM 2018 ; Conference date: 01-12-2018 Through 05-12-2018",

}

Chang, CC, Chen, PC, Hudec, B, Liu, P-T & Hou, T-H 2019, Interchangeable Hebbian and Anti-Hebbian STDP Applied to Supervised Learning in Spiking Neural Network. in 2018 IEEE International Electron Devices Meeting, IEDM 2018., 8614648, Technical Digest - International Electron Devices Meeting, IEDM, vol. 2018-December, Institute of Electrical and Electronics Engineers Inc., pp. 15.5.1-15.5.4, 64th Annual IEEE International Electron Devices Meeting, IEDM 2018, San Francisco, United States, 1/12/18. https://doi.org/10.1109/IEDM.2018.8614648

Interchangeable Hebbian and Anti-Hebbian STDP Applied to Supervised Learning in Spiking Neural Network. / Chang, Che Chia; Chen, Pin Chun; Hudec, Boris et al.
2018 IEEE International Electron Devices Meeting, IEDM 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 15.5.1-15.5.4 8614648 (Technical Digest - International Electron Devices Meeting, IEDM; Vol. 2018-December).

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

TY - GEN

T1 - Interchangeable Hebbian and Anti-Hebbian STDP Applied to Supervised Learning in Spiking Neural Network

AU - Chang, Che Chia

AU - Chen, Pin Chun

AU - Hudec, Boris

AU - Liu, Po-Tsun

AU - Hou, Tuo-Hung

PY - 2019/1/16

Y1 - 2019/1/16

N2 - This work provides a complete framework, including device, architecture, and algorithm, for implementing bio-inspired supervised spiking neural networks (SNNs) on hardware. An analog synapse with atypical dual bipolar resistive-switching (D-BRS) modes demonstrates interchangeable Hebbian spiking-timing-dependent plasticity (STDP) and anti-Hebbian STDP, and it is capable of implementing supervised ReSuMe SNNs in crossbar arrays. By using an 'exchange' update scheme, accurate supervised learning (∼96% for MNIST) is achieved in a compact network.

AB - This work provides a complete framework, including device, architecture, and algorithm, for implementing bio-inspired supervised spiking neural networks (SNNs) on hardware. An analog synapse with atypical dual bipolar resistive-switching (D-BRS) modes demonstrates interchangeable Hebbian spiking-timing-dependent plasticity (STDP) and anti-Hebbian STDP, and it is capable of implementing supervised ReSuMe SNNs in crossbar arrays. By using an 'exchange' update scheme, accurate supervised learning (∼96% for MNIST) is achieved in a compact network.

UR - http://www.scopus.com/inward/record.url?scp=85061785057&partnerID=8YFLogxK

U2 - 10.1109/IEDM.2018.8614648

DO - 10.1109/IEDM.2018.8614648

M3 - Conference contribution

AN - SCOPUS:85061785057

T3 - Technical Digest - International Electron Devices Meeting, IEDM

SP - 15.5.1-15.5.4

BT - 2018 IEEE International Electron Devices Meeting, IEDM 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 64th Annual IEEE International Electron Devices Meeting, IEDM 2018

Y2 - 1 December 2018 through 5 December 2018

ER -

Chang CC, Chen PC, Hudec B, Liu P-T , Hou T-H. Interchangeable Hebbian and Anti-Hebbian STDP Applied to Supervised Learning in Spiking Neural Network. In 2018 IEEE International Electron Devices Meeting, IEDM 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 15.5.1-15.5.4. 8614648. (Technical Digest - International Electron Devices Meeting, IEDM). doi: 10.1109/IEDM.2018.8614648

Interchangeable Hebbian and Anti-Hebbian STDP Applied to Supervised Learning in Spiking Neural Network

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this