skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

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.

Authors:
ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]
  1. ORNL
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1468265
DOE Contract Number:  
AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: Neuromorphic Computing Symposia, Knoxville, TN, USA, July 17-19, 2017
Country of Publication:
United States
Language:
English

Citation Formats

Hamilton, Kathleen E., Imam, Neena, and Humble, Travis S. Community detection with spiking neural networks for neuromorphic hardware. United States: N. p., 2017. Web. doi:10.1145/3183584.3183621.
Hamilton, Kathleen E., Imam, Neena, & Humble, Travis S. Community detection with spiking neural networks for neuromorphic hardware. United States. doi:10.1145/3183584.3183621.
Hamilton, Kathleen E., Imam, Neena, and Humble, Travis S. Sat . "Community detection with spiking neural networks for neuromorphic hardware". United States. doi:10.1145/3183584.3183621. https://www.osti.gov/servlets/purl/1468265.
@article{osti_1468265,
title = {Community detection with spiking neural networks for neuromorphic hardware},
author = {Hamilton, Kathleen E. and Imam, Neena and Humble, Travis S.},
abstractNote = {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.},
doi = {10.1145/3183584.3183621},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2017},
month = {7}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:

Works referenced in this record:

Neural networks and physical systems with emergent collective computational abilities.
journal, April 1982

  • Hopfield, J. J.
  • Proceedings of the National Academy of Sciences, Vol. 79, Issue 8
  • DOI: 10.1073/pnas.79.8.2554

Spike-Train Communities: Finding Groups of Similar Spike Trains
journal, February 2011


Community structure in social and biological networks
journal, June 2002

  • Girvan, M.; Newman, M. E. J.
  • Proceedings of the National Academy of Sciences, Vol. 99, Issue 12
  • DOI: 10.1073/pnas.122653799

Graph partitioning using annealed neural networks
journal, June 1990

  • Van den Bout, D. E.; Miller, T. K.
  • IEEE Transactions on Neural Networks, Vol. 1, Issue 2
  • DOI: 10.1109/72.80231

Community detection in graphs
journal, February 2010


Networks of spiking neurons can emulate arbitrary Hopfield nets in temporal coding
journal, January 1997

  • Maass, Wolfgang; Natschläger, Thomas
  • Network: Computation in Neural Systems, Vol. 8, Issue 4
  • DOI: 10.1088/0954-898X_8_4_002

Complex networks: Structure and dynamics
journal, February 2006


Neurons with graded response have collective computational properties like those of two-state neurons.
journal, May 1984


Clustering and community detection in directed networks: A survey
journal, December 2013


On the equivalence of the label propagation method of community detection and a Potts model approach
journal, August 2008

  • Tibély, Gergely; Kertész, János
  • Physica A: Statistical Mechanics and its Applications, Vol. 387, Issue 19-20
  • DOI: 10.1016/j.physa.2008.04.024