Community detection with spiking neural networks for neuromorphic hardware∗

Kathleen E. Hamilton; Neena Imam; Travis S. Humble

doi:10.1145/3183584.3183621

Community detection with spiking neural networks for neuromorphic hardware^∗

Kathleen E. Hamilton, Neena Imam, Travis S. Humble

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

3 Scopus citations

Abstract

We present results related to the performance of an algorithm for community detection which incorporates event-driven computation. We define a mapping which takes a graph G to a system of symmetrically connected, spiking neurons and use spike train similarities to identify vertex communities. On a random graph with 128 vertices and known community structure we show how our approach can be used to identify individual communities from spiking neuron responses.

Original language	English
Title of host publication	Proceedings of Neuromorphic Computing Symposium, NCS 2017
Publisher	Association for Computing Machinery
ISBN (Electronic)	9781450364423
DOIs	https://doi.org/10.1145/3183584.3183621
State	Published - Jul 17 2017
Event	2017 Neuromorphic Computing Symposium, NCS 2017 - Knoxville, United States Duration: Jul 17 2017 → Jul 19 2017

Publication series

Name	ACM International Conference Proceeding Series
Volume	2017-July

Conference

Conference	2017 Neuromorphic Computing Symposium, NCS 2017
Country/Territory	United States
City	Knoxville
Period	07/17/17 → 07/19/17

Funding

This work was supported by the United States Department of Defense and used resources of the Computational Research and Development Programs at Oak Ridge National Laboratory.

Keywords

Community detection
Neuromorphic
Spiking neural networks

Access to Document

10.1145/3183584.3183621

Cite this

@inproceedings{f3967bb850bb41a1a6d15f412a3a2305,

title = "Community detection with spiking neural networks for neuromorphic hardware∗",

abstract = "We present results related to the performance of an algorithm for community detection which incorporates event-driven computation. We define a mapping which takes a graph G to a system of symmetrically connected, spiking neurons and use spike train similarities to identify vertex communities. On a random graph with 128 vertices and known community structure we show how our approach can be used to identify individual communities from spiking neuron responses.",

keywords = "Community detection, Neuromorphic, Spiking neural networks",

author = "Hamilton, {Kathleen E.} and Neena Imam and Humble, {Travis S.}",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computing Machinery.; 2017 Neuromorphic Computing Symposium, NCS 2017 ; Conference date: 17-07-2017 Through 19-07-2017",

year = "2017",

month = jul,

day = "17",

doi = "10.1145/3183584.3183621",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

booktitle = "Proceedings of Neuromorphic Computing Symposium, NCS 2017",

}

Hamilton, KE, Imam, N & Humble, TS 2017, Community detection with spiking neural networks for neuromorphic hardware^∗. in Proceedings of Neuromorphic Computing Symposium, NCS 2017., a9, ACM International Conference Proceeding Series, vol. 2017-July, Association for Computing Machinery, 2017 Neuromorphic Computing Symposium, NCS 2017, Knoxville, United States, 07/17/17. https://doi.org/10.1145/3183584.3183621

Community detection with spiking neural networks for neuromorphic hardware^∗. / Hamilton, Kathleen E.; Imam, Neena; Humble, Travis S.
Proceedings of Neuromorphic Computing Symposium, NCS 2017. Association for Computing Machinery, 2017. a9 (ACM International Conference Proceeding Series; Vol. 2017-July).

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

TY - GEN

T1 - Community detection with spiking neural networks for neuromorphic hardware∗

AU - Hamilton, Kathleen E.

AU - Imam, Neena

AU - Humble, Travis S.

PY - 2017/7/17

Y1 - 2017/7/17

N2 - We present results related to the performance of an algorithm for community detection which incorporates event-driven computation. We define a mapping which takes a graph G to a system of symmetrically connected, spiking neurons and use spike train similarities to identify vertex communities. On a random graph with 128 vertices and known community structure we show how our approach can be used to identify individual communities from spiking neuron responses.

AB - We present results related to the performance of an algorithm for community detection which incorporates event-driven computation. We define a mapping which takes a graph G to a system of symmetrically connected, spiking neurons and use spike train similarities to identify vertex communities. On a random graph with 128 vertices and known community structure we show how our approach can be used to identify individual communities from spiking neuron responses.

KW - Community detection

KW - Neuromorphic

KW - Spiking neural networks

UR - http://www.scopus.com/inward/record.url?scp=85047000645&partnerID=8YFLogxK

U2 - 10.1145/3183584.3183621

DO - 10.1145/3183584.3183621

M3 - Conference contribution

AN - SCOPUS:85047000645

T3 - ACM International Conference Proceeding Series

BT - Proceedings of Neuromorphic Computing Symposium, NCS 2017

PB - Association for Computing Machinery

T2 - 2017 Neuromorphic Computing Symposium, NCS 2017

Y2 - 17 July 2017 through 19 July 2017

ER -