Solving constraint satisfaction problems with networks of spiking neurons

Zeno Jonke, Stefan Habenschuss, Wolfgang Maass

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Network of neurons in the brain apply unlike processors in our current generation of computer hardware an event-based processing strategy, where short pulses (spikes) are emitted sparsely by neurons to signal the occurrence of an event at a particular point in time. Such spike-based computations promise to be substantially more power-efficient than traditional clocked processing schemes. However it turns out to be surprisingly difficult to design networks of spiking neurons that can solve difficult computational problems on the level of single spikes, rather than rates of spikes. We present here a new method for designing networks of spiking neurons via an energy function. Furthermore we show how the energy function of a network of stochastically firing neurons can be shaped in a transparent manner by composing the networks of simple stereotypical network motifs. We show that this design approach enables networks of spiking neurons to produce approximate solutions to difficult (NP-hard) constraint satisfaction problems from the domains of planning/optimization and verification/logical inference. The resulting networks employ noise as a computational resource. Nevertheless the timing of spikes plays an essential role in their computations. Furthermore, networks of spiking neurons carry out for the Traveling Salesman Problem a more efficient stochastic search for good solutions compared with stochastic artificial neural networks (Boltzmann machines) and Gibbs sampling.
Original languageEnglish
JournalFrontiers in neuroscience
DOIs
Publication statusPublished - 2016

Fingerprint

Neurons
Noise
Brain

Cite this

Solving constraint satisfaction problems with networks of spiking neurons. / Jonke, Zeno; Habenschuss, Stefan; Maass, Wolfgang.

In: Frontiers in neuroscience, 2016.

Research output: Contribution to journalArticleResearchpeer-review

@article{5acec5b58c654223a4e3b53cc507e15b,
title = "Solving constraint satisfaction problems with networks of spiking neurons",
abstract = "Network of neurons in the brain apply unlike processors in our current generation of computer hardware an event-based processing strategy, where short pulses (spikes) are emitted sparsely by neurons to signal the occurrence of an event at a particular point in time. Such spike-based computations promise to be substantially more power-efficient than traditional clocked processing schemes. However it turns out to be surprisingly difficult to design networks of spiking neurons that can solve difficult computational problems on the level of single spikes, rather than rates of spikes. We present here a new method for designing networks of spiking neurons via an energy function. Furthermore we show how the energy function of a network of stochastically firing neurons can be shaped in a transparent manner by composing the networks of simple stereotypical network motifs. We show that this design approach enables networks of spiking neurons to produce approximate solutions to difficult (NP-hard) constraint satisfaction problems from the domains of planning/optimization and verification/logical inference. The resulting networks employ noise as a computational resource. Nevertheless the timing of spikes plays an essential role in their computations. Furthermore, networks of spiking neurons carry out for the Traveling Salesman Problem a more efficient stochastic search for good solutions compared with stochastic artificial neural networks (Boltzmann machines) and Gibbs sampling.",
author = "Zeno Jonke and Stefan Habenschuss and Wolfgang Maass",
year = "2016",
doi = "10.3389/fnins.2016.00118",
language = "English",
journal = "Frontiers in neuroscience",
issn = "1662-4548",
publisher = "Frontiers Research Foundation",

}

TY - JOUR

T1 - Solving constraint satisfaction problems with networks of spiking neurons

AU - Jonke, Zeno

AU - Habenschuss, Stefan

AU - Maass, Wolfgang

PY - 2016

Y1 - 2016

N2 - Network of neurons in the brain apply unlike processors in our current generation of computer hardware an event-based processing strategy, where short pulses (spikes) are emitted sparsely by neurons to signal the occurrence of an event at a particular point in time. Such spike-based computations promise to be substantially more power-efficient than traditional clocked processing schemes. However it turns out to be surprisingly difficult to design networks of spiking neurons that can solve difficult computational problems on the level of single spikes, rather than rates of spikes. We present here a new method for designing networks of spiking neurons via an energy function. Furthermore we show how the energy function of a network of stochastically firing neurons can be shaped in a transparent manner by composing the networks of simple stereotypical network motifs. We show that this design approach enables networks of spiking neurons to produce approximate solutions to difficult (NP-hard) constraint satisfaction problems from the domains of planning/optimization and verification/logical inference. The resulting networks employ noise as a computational resource. Nevertheless the timing of spikes plays an essential role in their computations. Furthermore, networks of spiking neurons carry out for the Traveling Salesman Problem a more efficient stochastic search for good solutions compared with stochastic artificial neural networks (Boltzmann machines) and Gibbs sampling.

AB - Network of neurons in the brain apply unlike processors in our current generation of computer hardware an event-based processing strategy, where short pulses (spikes) are emitted sparsely by neurons to signal the occurrence of an event at a particular point in time. Such spike-based computations promise to be substantially more power-efficient than traditional clocked processing schemes. However it turns out to be surprisingly difficult to design networks of spiking neurons that can solve difficult computational problems on the level of single spikes, rather than rates of spikes. We present here a new method for designing networks of spiking neurons via an energy function. Furthermore we show how the energy function of a network of stochastically firing neurons can be shaped in a transparent manner by composing the networks of simple stereotypical network motifs. We show that this design approach enables networks of spiking neurons to produce approximate solutions to difficult (NP-hard) constraint satisfaction problems from the domains of planning/optimization and verification/logical inference. The resulting networks employ noise as a computational resource. Nevertheless the timing of spikes plays an essential role in their computations. Furthermore, networks of spiking neurons carry out for the Traveling Salesman Problem a more efficient stochastic search for good solutions compared with stochastic artificial neural networks (Boltzmann machines) and Gibbs sampling.

U2 - 10.3389/fnins.2016.00118

DO - 10.3389/fnins.2016.00118

M3 - Article

JO - Frontiers in neuroscience

JF - Frontiers in neuroscience

SN - 1662-4548

ER -