Computing with Spikes: The Advantage of Fine-Grained Timing
Abstract
Neural-inspired spike-based computing machines often claim to achieve considerable advantages in terms of energy and time efficiency by using spikes for computation and communication. However, fundamental questions about spike-based computation remain unanswered. For instance, how much advantage do spike-based approaches have over conventional methods, and under what circumstances does spike-based computing provide a comparative advantage? Simply implementing existing algorithms using spikes as the medium of computation and communication is not guaranteed to yield an advantage. Here, we demonstrate that spike-based communication and computation within algorithms can increase throughput, and they can decrease energy cost in some cases. We present several spiking algorithms, including sorting a set of numbers in ascending/descending order, as well as finding the maximum or minimum or median of a set of numbers. We also provide an example application: a spiking median-filtering approach for image processing providing a low-energy, parallel implementation. Furthermore, the algorithms and analyses presented here demonstrate that spiking algorithms can provide performance advantages and offer efficient computation of fundamental operations useful in more complex algorithms.
- Authors:
-
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Publication Date:
- Research Org.:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA)
- OSTI Identifier:
- 1466763
- Report Number(s):
- SAND-2018-9039J
Journal ID: ISSN 0899-7667; 667190
- Grant/Contract Number:
- AC04-94AL85000
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Neural Computation
- Additional Journal Information:
- Journal Volume: 30; Journal Issue: 10; Journal ID: ISSN 0899-7667
- Publisher:
- MIT Press
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; Spiking Neural Network; Temporal Coding; Parallel Sorting; Sparse Activation; Median-filtering
Citation Formats
Verzi, Stephen J., Rothganger, Fredrick, Parekh, Ojas D., Quach, Tu -Thach, Miner, Nadine E., Vineyard, Craig M., James, Conrad D., and Aimone, James B. Computing with Spikes: The Advantage of Fine-Grained Timing. United States: N. p., 2018.
Web. doi:10.1162/neco_a_01113.
Verzi, Stephen J., Rothganger, Fredrick, Parekh, Ojas D., Quach, Tu -Thach, Miner, Nadine E., Vineyard, Craig M., James, Conrad D., & Aimone, James B. Computing with Spikes: The Advantage of Fine-Grained Timing. United States. https://doi.org/10.1162/neco_a_01113
Verzi, Stephen J., Rothganger, Fredrick, Parekh, Ojas D., Quach, Tu -Thach, Miner, Nadine E., Vineyard, Craig M., James, Conrad D., and Aimone, James B. Wed .
"Computing with Spikes: The Advantage of Fine-Grained Timing". United States. https://doi.org/10.1162/neco_a_01113. https://www.osti.gov/servlets/purl/1466763.
@article{osti_1466763,
title = {Computing with Spikes: The Advantage of Fine-Grained Timing},
author = {Verzi, Stephen J. and Rothganger, Fredrick and Parekh, Ojas D. and Quach, Tu -Thach and Miner, Nadine E. and Vineyard, Craig M. and James, Conrad D. and Aimone, James B.},
abstractNote = {Neural-inspired spike-based computing machines often claim to achieve considerable advantages in terms of energy and time efficiency by using spikes for computation and communication. However, fundamental questions about spike-based computation remain unanswered. For instance, how much advantage do spike-based approaches have over conventional methods, and under what circumstances does spike-based computing provide a comparative advantage? Simply implementing existing algorithms using spikes as the medium of computation and communication is not guaranteed to yield an advantage. Here, we demonstrate that spike-based communication and computation within algorithms can increase throughput, and they can decrease energy cost in some cases. We present several spiking algorithms, including sorting a set of numbers in ascending/descending order, as well as finding the maximum or minimum or median of a set of numbers. We also provide an example application: a spiking median-filtering approach for image processing providing a low-energy, parallel implementation. Furthermore, the algorithms and analyses presented here demonstrate that spiking algorithms can provide performance advantages and offer efficient computation of fundamental operations useful in more complex algorithms.},
doi = {10.1162/neco_a_01113},
journal = {Neural Computation},
number = 10,
volume = 30,
place = {United States},
year = {Wed Jul 18 00:00:00 EDT 2018},
month = {Wed Jul 18 00:00:00 EDT 2018}
}
Web of Science
Works referenced in this record:
Adaptive impulse detection using center-weighted median filters
journal, January 2001
- Chen, T.
- IEEE Signal Processing Letters, Vol. 8, Issue 1
Spike-Based Population Coding and Working Memory
journal, February 2011
- Boerlin, Martin; Denève, Sophie
- PLoS Computational Biology, Vol. 7, Issue 2
Pattern recognition computation using action potential timing for stimulus representation
journal, July 1995
- Hopfield, J. J.
- Nature, Vol. 376, Issue 6535
Developing and applying a toolkit from a general neurocomputational framework
journal, June 1999
- Eliasmith, Chris; Anderson, Charles H.
- Neurocomputing, Vol. 26-27
A million spiking-neuron integrated circuit with a scalable communication network and interface
journal, August 2014
- Merolla, P. A.; Arthur, J. V.; Alvarez-Icaza, R.
- Science, Vol. 345, Issue 6197
Role of experience and oscillations in transforming a rate code into a temporal code
journal, June 2002
- Mehta, M. R.; Lee, A. K.; Wilson, M. A.
- Nature, Vol. 417, Issue 6890
Lapicque’s introduction of the integrate-and-fire model neuron (1907)
journal, November 1999
- Abbott, L. F.
- Brain Research Bulletin, Vol. 50, Issue 5-6
Distinct relationships of parietal and prefrontal cortices to evidence accumulation
journal, January 2015
- Hanks, Timothy D.; Kopec, Charles D.; Brunton, Bingni W.
- Nature, Vol. 520, Issue 7546
Dynamics of decision-making: from evidence accumulation to preference and belief
journal, January 2013
- Usher, Marius; Tsetsos, Konstantinos; Yu, Erica C.
- Frontiers in Psychology, Vol. 4
STICK: Spike Time Interval Computational Kernel, a Framework for General Purpose Computation Using Neurons, Precise Timing, Delays, and Synchrony
journal, November 2015
- Lagorce, Xavier; Benosman, Ryad
- Neural Computation, Vol. 27, Issue 11
Routing, merging, and sorting on parallel models of computation
journal, February 1985
- Borodin, A.; Hopcroft, J. E.
- Journal of Computer and System Sciences, Vol. 30, Issue 1
A universal noise removal algorithm with an impulse detector
journal, November 2005
- Garnett, R.; Huegerich, T.; Chui, C.
- IEEE Transactions on Image Processing, Vol. 14, Issue 11
On the Computational Power of Winner-Take-All
journal, November 2000
- Maass, Wolfgang
- Neural Computation, Vol. 12, Issue 11
Computational Account of Spontaneous Activity as a Signature of Predictive Coding
journal, January 2017
- Koren, Veronika; Denève, Sophie
- PLOS Computational Biology, Vol. 13, Issue 1
Predictive Coding of Dynamical Variables in Balanced Spiking Networks
journal, November 2013
- Boerlin, Martin; Machens, Christian K.; Denève, Sophie
- PLoS Computational Biology, Vol. 9, Issue 11
Expressibility and Parallel Complexity
journal, June 1989
- Immerman, Neil
- SIAM Journal on Computing, Vol. 18, Issue 3
Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations
journal, May 2014
- Benjamin, Ben Varkey; Gao, Peiran; McQuinn, Emmett
- Proceedings of the IEEE, Vol. 102, Issue 5
An Improved Median Filtering Algorithm for Image Noise Reduction
journal, January 2012
- Zhu, Youlian; Huang, Cheng
- Physics Procedia, Vol. 25
Improving Spiking Dynamical Networks: Accurate Delays, Higher-Order Synapses, and Time Cells
journal, March 2018
- Voelker, Aaron R.; Eliasmith, Chris
- Neural Computation, Vol. 30, Issue 3
A discrete time neural network model with spiking neurons: Rigorous results on the spontaneous dynamics
journal, September 2007
- Cessac, B.
- Journal of Mathematical Biology, Vol. 56, Issue 3
Belief Propagation in Networks of Spiking Neurons
journal, September 2009
- Steimer, Andreas; Maass, Wolfgang; Douglas, Rodney
- Neural Computation, Vol. 21, Issue 9
Spike-based strategies for rapid processing
journal, July 2001
- Thorpe, Simon; Delorme, Arnaud; Van Rullen, Rufin
- Neural Networks, Vol. 14, Issue 6-7
The median and its extensions
journal, July 2011
- Beliakov, Gleb; Bustince, Humberto; Fernandez, Javier
- Fuzzy Sets and Systems, Vol. 175, Issue 1
A parallel median algorithm
journal, April 1985
- Cole, Richard; Yap, Chee K.
- Information Processing Letters, Vol. 20, Issue 3
The SpiNNaker Project
journal, May 2014
- Furber, Steve B.; Galluppi, Francesco; Temple, Steve
- Proceedings of the IEEE, Vol. 102, Issue 5
Computation with Spikes in a Winner-Take-All Network
journal, September 2009
- Oster, Matthias; Douglas, Rodney; Liu, Shih-Chii
- Neural Computation, Vol. 21, Issue 9
General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results
journal, December 2003
- Šíma, Jiří; Orponen, Pekka
- Neural Computation, Vol. 15, Issue 12
Spike times make sense
journal, January 2005
- VanRullen, Rufin; Guyonneau, Rudy; Thorpe, Simon J.
- Trends in Neurosciences, Vol. 28, Issue 1
O(log*n) algorithms on a Sum-CRCW PRAM
journal, December 2006
- Eisenstat, S. C.
- Computing, Vol. 79, Issue 1
An optimal algorithm for parallel selection
journal, July 1984
- Akl, Selim G.
- Information Processing Letters, Vol. 19, Issue 1
Accumulation of Evidence during Sequential Decision Making: The Importance of Top-Down Factors
journal, January 2010
- de Lange, F. P.; Jensen, O.; Dehaene, S.
- Journal of Neuroscience, Vol. 30, Issue 2
Parallelism in Comparison Problems
journal, September 1975
- Valiant, Leslie G.
- SIAM Journal on Computing, Vol. 4, Issue 3
Convolutional networks for fast, energy-efficient neuromorphic computing
journal, September 2016
- Esser, Steven K.; Merolla, Paul A.; Arthur, John V.
- Proceedings of the National Academy of Sciences, Vol. 113, Issue 41
Contour Enhancement, Short Term Memory, and Constancies in Reverberating Neural Networks
journal, September 1973
- Grossberg, Stephen
- Studies in Applied Mathematics, Vol. 52, Issue 3
Finding the maximum, merging, and sorting in a parallel computation model
journal, March 1981
- Shiloach, Yossi; Vishkin, Uzi
- Journal of Algorithms, Vol. 2, Issue 1
Neural codes: Firing rates and beyond
journal, November 1997
- Gerstner, W.; Kreiter, A. K.; Markram, H.
- Proceedings of the National Academy of Sciences, Vol. 94, Issue 24
Local limit theorems for the maxima of discrete random variables
journal, July 1980
- Anderson, C. W.
- Mathematical Proceedings of the Cambridge Philosophical Society, Vol. 88, Issue 1
A quantitative description of membrane current and its application to conduction and excitation in nerve
journal, August 1952
- Hodgkin, A. L.; Huxley, A. F.
- The Journal of Physiology, Vol. 117, Issue 4
Networks of spiking neurons: The third generation of neural network models
journal, December 1997
- Maass, Wolfgang
- Neural Networks, Vol. 10, Issue 9
How Precise is Neuronal Synchronization?
journal, May 1995
- König, Peter; Engel, Andreas K.; Roelfsema, Pieter R.
- Neural Computation, Vol. 7, Issue 3
A logical calculus of the ideas immanent in nervous activity
journal, December 1943
- McCulloch, Warren S.; Pitts, Walter
- The Bulletin of Mathematical Biophysics, Vol. 5, Issue 4
REVIEW ARTICLE: Neuronal coding and spiking randomness: Neuronal coding and spiking randomness
journal, November 2007
- Kostal, Lubomir; Lansky, Petr; Rospars, Jean-Pierre
- European Journal of Neuroscience, Vol. 26, Issue 10
Bayesian Spiking Neurons I: Inference
journal, January 2008
- Deneve, Sophie
- Neural Computation, Vol. 20, Issue 1
Fine analog coding minimizes information transmission
journal, January 1996
- Softky, William R.
- Neural Networks, Vol. 9, Issue 1
Efficient codes and balanced networks
journal, February 2016
- Denève, Sophie; Machens, Christian K.
- Nature Neuroscience, Vol. 19, Issue 3
Polychronization: Computation with Spikes
journal, February 2006
- Izhikevich, Eugene M.
- Neural Computation, Vol. 18, Issue 2
Rate coding versus temporal order coding: a theoretical approach
journal, November 1998
- Gautrais, Jacques; Thorpe, Simon
- Biosystems, Vol. 48, Issue 1-3
On the Power of some pram Models
journal, January 1999
- Akl, Selim G.; Chen, Lin
- Parallel Algorithms and Applications, Vol. 13, Issue 4
Generalized Integrate-and-Fire Models of Neuronal Activity Approximate Spike Trains of a Detailed Model to a High Degree of Accuracy
journal, August 2004
- Jolivet, Renaud; Lewis, Timothy J.; Gerstner, Wulfram
- Journal of Neurophysiology, Vol. 92, Issue 2
A Large-Scale Model of the Functioning Brain
journal, November 2012
- Eliasmith, C.; Stewart, T. C.; Choo, X.
- Science, Vol. 338, Issue 6111
A spiking neural network architecture for nonlinear function approximation
journal, July 2001
- Iannella, Nicolangelo; Back, Andrew D.
- Neural Networks, Vol. 14, Issue 6-7
Optimization-based computation with spiking neurons
conference, May 2017
- Verzi, Stephen J.; Vineyard, Craig M.; Vugrin, Eric D.
- 2017 International Joint Conference on Neural Networks (IJCNN)
Works referencing / citing this record:
A critical survey of STDP in Spiking Neural Networks for Pattern Recognition
conference, July 2020
- Vigneron, Alex; Martinet, Jean
- 2020 International Joint Conference on Neural Networks (IJCNN)