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

Title: Sparse Hardware Embedding of Spiking Neuron Systems for Community Detection

Abstract

We study the applicability of spiking neural networks and neuromorphic hardware for solving general optimization problems without the use of adaptive training or learning algorithms. We leverage the dynamics of Hopfield networks and spin-glass systems to construct a fully connected spiking neural system to generate synchronous spike responses indicative of the underlying community structure in an undirected, unweighted graph. Mapping this fully connected system to current generation neuromorphic hardware is done by embedding sparse tree graphs to generate only the leading-order spiking dynamics. Here, we demonstrate that for a chosen set of benchmark graphs, the spike responses generated on a current generation neuromorphic processor can improve the stability of graph partitions and non-overlapping communities can be identified even with the loss of higher-order spiking behavior if the graphs are sufficiently dense. For sparse graphs, the loss of higher-order spiking behavior improves the stability of certain graph partitions but does not retrieve the known community memberships.

Authors:
ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]
  1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1504017
Grant/Contract Number:  
AC05-00OR22725
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
ACM Journal on Emerging Technologies in Computing Systems
Additional Journal Information:
Journal Volume: 14; Journal Issue: 4; Journal ID: ISSN 1550-4832
Publisher:
Association for Computing Machinery
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; optimization; community detection; neural network; graph algorithm

Citation Formats

Hamilton, Kathleen E., Imam, Neena, and Humble, Travis S. Sparse Hardware Embedding of Spiking Neuron Systems for Community Detection. United States: N. p., 2018. Web. doi:10.1145/3223048.
Hamilton, Kathleen E., Imam, Neena, & Humble, Travis S. Sparse Hardware Embedding of Spiking Neuron Systems for Community Detection. United States. doi:10.1145/3223048.
Hamilton, Kathleen E., Imam, Neena, and Humble, Travis S. Thu . "Sparse Hardware Embedding of Spiking Neuron Systems for Community Detection". United States. doi:10.1145/3223048.
@article{osti_1504017,
title = {Sparse Hardware Embedding of Spiking Neuron Systems for Community Detection},
author = {Hamilton, Kathleen E. and Imam, Neena and Humble, Travis S.},
abstractNote = {We study the applicability of spiking neural networks and neuromorphic hardware for solving general optimization problems without the use of adaptive training or learning algorithms. We leverage the dynamics of Hopfield networks and spin-glass systems to construct a fully connected spiking neural system to generate synchronous spike responses indicative of the underlying community structure in an undirected, unweighted graph. Mapping this fully connected system to current generation neuromorphic hardware is done by embedding sparse tree graphs to generate only the leading-order spiking dynamics. Here, we demonstrate that for a chosen set of benchmark graphs, the spike responses generated on a current generation neuromorphic processor can improve the stability of graph partitions and non-overlapping communities can be identified even with the loss of higher-order spiking behavior if the graphs are sufficiently dense. For sparse graphs, the loss of higher-order spiking behavior improves the stability of certain graph partitions but does not retrieve the known community memberships.},
doi = {10.1145/3223048},
journal = {ACM Journal on Emerging Technologies in Computing Systems},
issn = {1550-4832},
number = 4,
volume = 14,
place = {United States},
year = {2018},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on November 1, 2019
Publisher's Version of Record

Save / Share: