Sparse Hardware Embedding of Spiking Neuron Systems for Community Detection

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

doi:10.1145/3223048

Sparse Hardware Embedding of Spiking Neuron Systems for Community Detection

Journal Article · Thu Nov 01 00:00:00 EDT 2018 · ACM Journal on Emerging Technologies in Computing Systems

DOI:https://doi.org/10.1145/3223048· OSTI ID:1504017

^[1]; ^[1]; ^[1]

Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

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.

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States); Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF)

Sponsoring Organization:: DOE Office of Science; USDOE

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 1504017

Journal Information:: ACM Journal on Emerging Technologies in Computing Systems, Journal Name: ACM Journal on Emerging Technologies in Computing Systems Journal Issue: 4 Vol. 14; ISSN 1550-4832

Publisher:: Association for Computing MachineryCopyright Statement

Country of Publication:: United States

Language:: English

References (12)

Convolutional networks for fast, energy-efficient neuromorphic computing Esser, Steven K.; Merolla, Paul A.; Arthur, John V. Proceedings of the National Academy of Sciences, Vol. 113, Issue 41 https://doi.org/10.1073/pnas.1604850113	journal	September 2016
Neural networks and physical systems with emergent collective computational abilities. Hopfield, J. J. Proceedings of the National Academy of Sciences, Vol. 79, Issue 8 https://doi.org/10.1073/pnas.79.8.2554	journal	April 1982
Multiresolution community detection for megascale networks by information-based replica correlations Ronhovde, Peter; Nussinov, Zohar Physical Review E, Vol. 80, Issue 1 https://doi.org/10.1103/PhysRevE.80.016109	journal	July 2009
Local resolution-limit-free Potts model for community detection Ronhovde, Peter; Nussinov, Zohar Physical Review E, Vol. 81, Issue 4 https://doi.org/10.1103/PhysRevE.81.046114	journal	April 2010
Cognitive computing building block: A versatile and efficient digital neuron model for neurosynaptic cores Cassidy, Andrew S.; Merolla, Paul; Arthur, John V. 2013 International Joint Conference on Neural Networks (IJCNN 2013 - Dallas), The 2013 International Joint Conference on Neural Networks (IJCNN) https://doi.org/10.1109/IJCNN.2013.6707077	conference	August 2013
Gibbs sampling with low-power spiking digital neurons Das, Srinjoy; Pedroni, Bruno Umbria; Merolla, Paul 2015 IEEE International Symposium on Circuits and Systems (ISCAS) https://doi.org/10.1109/ISCAS.2015.7169244	conference	May 2015
Mapping Generative Models onto a Network of Digital Spiking Neurons Pedroni, Bruno U.; Das, Srinjoy; Arthur, John V. IEEE Transactions on Biomedical Circuits and Systems, Vol. 10, Issue 4 https://doi.org/10.1109/TBCAS.2016.2539352	journal	August 2016
A million spiking-neuron integrated circuit with a scalable communication network and interface Merolla, P. A.; Arthur, J. V.; Alvarez-Icaza, R. Science, Vol. 345, Issue 6197 https://doi.org/10.1126/science.1254642	journal	August 2014
Selection of intrinsic horizontal connections in the visual cortex by correlated neuronal activity Lowel, S.; Singer, W. Science, Vol. 255, Issue 5041 https://doi.org/10.1126/science.1372754	journal	January 1992
Community detection with spiking neural networks for neuromorphic hardware Hamilton, Kathleen E.; Imam, Neena; Humble, Travis S. Proceedings of the Neuromorphic Computing Symposium on - NCS '17 https://doi.org/10.1145/3183584.3183621	conference	January 2017
Spike-Train Communities: Finding Groups of Similar Spike Trains Humphries, M. D. Journal of Neuroscience, Vol. 31, Issue 6 https://doi.org/10.1523/JNEUROSCI.2853-10.2011	journal	February 2011
Brian: a simulator for spiking neural networks in Python Goodman, Dan Frontiers in Neuroinformatics, Vol. 2 https://doi.org/10.3389/neuro.11.005.2008	journal	January 2008

Similar Records

Towards adaptive spiking label propagation

Conference · Sun Jul 01 00:00:00 EDT 2018 · OSTI ID:1479771

Towards adaptive spiking label propagation

Conference · Sun Jul 01 00:00:00 EDT 2018 · OSTI ID:1468094

Solving sparse finite element problems on neuromorphic hardware

Journal Article · Wed Nov 12 19:00:00 EST 2025 · Nature Machine Intelligence · OSTI ID:3006560

Related Subjects

97 MATHEMATICS AND COMPUTING
community detection
graph algorithm
neural network
optimization

Sparse Hardware Embedding of Spiking Neuron Systems for Community Detection

Citation Formats

References (12)

Similar Records

Related Subjects