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

Title: Towards adaptive spiking label propagation

Abstract

Graph algorithms are a new class of applications for neuromorphic hardware. Rather than adapting deep learning and standard neural network approaches to a low-precision spiking environment, we use spiking neurons to analyze undirected graphs (e.g., the underlying modular structure). While fully connected spin glass implementations of spiking label propagation have shown promising results on graphs with dense communities, identifying sparse communities remains difficult. This work focuses on steps towards an adaptive spike-based implementations of label propagation, utilizing sparse embeddings and synaptic plasticity. Sparser embeddings reduce the number of inhibitory connections, and synaptic plasticity is used to simultaneously amplify spike responses between neurons in the same community, while impeding spike responses across different communities. We present results on identifying communities in sparse graphs with very small communities.

Authors:
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:
1479771
DOE Contract Number:  
AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: International Conference on Neuromorphic Systems (ICONS) - Knoxville, Tennessee, United States of America - 7/23/2018 8:00:00 AM-7/26/2018 8:00:00 AM
Country of Publication:
United States
Language:
English

Citation Formats

Hamilton, Kathleen E., and Schuman, Catherine D. Towards adaptive spiking label propagation. United States: N. p., 2018. Web. doi:10.1145/3229884.3229897.
Hamilton, Kathleen E., & Schuman, Catherine D. Towards adaptive spiking label propagation. United States. doi:10.1145/3229884.3229897.
Hamilton, Kathleen E., and Schuman, Catherine D. Sun . "Towards adaptive spiking label propagation". United States. doi:10.1145/3229884.3229897. https://www.osti.gov/servlets/purl/1479771.
@article{osti_1479771,
title = {Towards adaptive spiking label propagation},
author = {Hamilton, Kathleen E. and Schuman, Catherine D.},
abstractNote = {Graph algorithms are a new class of applications for neuromorphic hardware. Rather than adapting deep learning and standard neural network approaches to a low-precision spiking environment, we use spiking neurons to analyze undirected graphs (e.g., the underlying modular structure). While fully connected spin glass implementations of spiking label propagation have shown promising results on graphs with dense communities, identifying sparse communities remains difficult. This work focuses on steps towards an adaptive spike-based implementations of label propagation, utilizing sparse embeddings and synaptic plasticity. Sparser embeddings reduce the number of inhibitory connections, and synaptic plasticity is used to simultaneously amplify spike responses between neurons in the same community, while impeding spike responses across different communities. We present results on identifying communities in sparse graphs with very small communities.},
doi = {10.1145/3229884.3229897},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2018},
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: