Brian2Loihi: An emulator for the neuromorphic chip Loihi using the spiking neural network simulator Brian

Developing intelligent neuromorphic solutions remains a challenging endeavor. It requires a solid conceptual understanding of the hardware's fundamental building blocks. Beyond this, accessible and user-friendly prototyping is crucial to speed up the design pipeline. We developed an open source...

Full description

Bibliographic Details
Main Authors: Carlo Michaelis, Andrew B. Lehr, Winfried Oed, Christian Tetzlaff
Format: Article
Language:English
Published: Frontiers Media S.A. 2022-11-01
Series:Frontiers in Neuroinformatics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fninf.2022.1015624/full
_version_ 1811231301274959872
author Carlo Michaelis
Carlo Michaelis
Andrew B. Lehr
Andrew B. Lehr
Winfried Oed
Winfried Oed
Christian Tetzlaff
Christian Tetzlaff
author_facet Carlo Michaelis
Carlo Michaelis
Andrew B. Lehr
Andrew B. Lehr
Winfried Oed
Winfried Oed
Christian Tetzlaff
Christian Tetzlaff
author_sort Carlo Michaelis
collection DOAJ
description Developing intelligent neuromorphic solutions remains a challenging endeavor. It requires a solid conceptual understanding of the hardware's fundamental building blocks. Beyond this, accessible and user-friendly prototyping is crucial to speed up the design pipeline. We developed an open source Loihi emulator based on the neural network simulator Brian that can easily be incorporated into existing simulation workflows. We demonstrate errorless Loihi emulation in software for a single neuron and for a recurrently connected spiking neural network. On-chip learning is also reviewed and implemented, with reasonable discrepancy due to stochastic rounding. This work provides a coherent presentation of Loihi's computational unit and introduces a new, easy-to-use Loihi prototyping package with the aim to help streamline conceptualization and deployment of new algorithms.
first_indexed 2024-04-12T10:42:26Z
format Article
id doaj.art-47a4df511e53499fb435efe68c5447f2
institution Directory Open Access Journal
issn 1662-5196
language English
last_indexed 2024-04-12T10:42:26Z
publishDate 2022-11-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neuroinformatics
spelling doaj.art-47a4df511e53499fb435efe68c5447f22022-12-22T03:36:33ZengFrontiers Media S.A.Frontiers in Neuroinformatics1662-51962022-11-011610.3389/fninf.2022.10156241015624Brian2Loihi: An emulator for the neuromorphic chip Loihi using the spiking neural network simulator BrianCarlo Michaelis0Carlo Michaelis1Andrew B. Lehr2Andrew B. Lehr3Winfried Oed4Winfried Oed5Christian Tetzlaff6Christian Tetzlaff7Department of Computational Neuroscience, University of Göttingen, Göttingen, GermanyBernstein Center for Computational Neuroscience, University of Göttingen, Göttingen, GermanyDepartment of Computational Neuroscience, University of Göttingen, Göttingen, GermanyBernstein Center for Computational Neuroscience, University of Göttingen, Göttingen, GermanyDepartment of Computational Neuroscience, University of Göttingen, Göttingen, GermanyBernstein Center for Computational Neuroscience, University of Göttingen, Göttingen, GermanyDepartment of Computational Neuroscience, University of Göttingen, Göttingen, GermanyBernstein Center for Computational Neuroscience, University of Göttingen, Göttingen, GermanyDeveloping intelligent neuromorphic solutions remains a challenging endeavor. It requires a solid conceptual understanding of the hardware's fundamental building blocks. Beyond this, accessible and user-friendly prototyping is crucial to speed up the design pipeline. We developed an open source Loihi emulator based on the neural network simulator Brian that can easily be incorporated into existing simulation workflows. We demonstrate errorless Loihi emulation in software for a single neuron and for a recurrently connected spiking neural network. On-chip learning is also reviewed and implemented, with reasonable discrepancy due to stochastic rounding. This work provides a coherent presentation of Loihi's computational unit and introduces a new, easy-to-use Loihi prototyping package with the aim to help streamline conceptualization and deployment of new algorithms.https://www.frontiersin.org/articles/10.3389/fninf.2022.1015624/fullneuromorphic computingLoihiBrian2emulatorspiking neural networkopen source
spellingShingle Carlo Michaelis
Carlo Michaelis
Andrew B. Lehr
Andrew B. Lehr
Winfried Oed
Winfried Oed
Christian Tetzlaff
Christian Tetzlaff
Brian2Loihi: An emulator for the neuromorphic chip Loihi using the spiking neural network simulator Brian
Frontiers in Neuroinformatics
neuromorphic computing
Loihi
Brian2
emulator
spiking neural network
open source
title Brian2Loihi: An emulator for the neuromorphic chip Loihi using the spiking neural network simulator Brian
title_full Brian2Loihi: An emulator for the neuromorphic chip Loihi using the spiking neural network simulator Brian
title_fullStr Brian2Loihi: An emulator for the neuromorphic chip Loihi using the spiking neural network simulator Brian
title_full_unstemmed Brian2Loihi: An emulator for the neuromorphic chip Loihi using the spiking neural network simulator Brian
title_short Brian2Loihi: An emulator for the neuromorphic chip Loihi using the spiking neural network simulator Brian
title_sort brian2loihi an emulator for the neuromorphic chip loihi using the spiking neural network simulator brian
topic neuromorphic computing
Loihi
Brian2
emulator
spiking neural network
open source
url https://www.frontiersin.org/articles/10.3389/fninf.2022.1015624/full
work_keys_str_mv AT carlomichaelis brian2loihianemulatorfortheneuromorphicchiploihiusingthespikingneuralnetworksimulatorbrian
AT carlomichaelis brian2loihianemulatorfortheneuromorphicchiploihiusingthespikingneuralnetworksimulatorbrian
AT andrewblehr brian2loihianemulatorfortheneuromorphicchiploihiusingthespikingneuralnetworksimulatorbrian
AT andrewblehr brian2loihianemulatorfortheneuromorphicchiploihiusingthespikingneuralnetworksimulatorbrian
AT winfriedoed brian2loihianemulatorfortheneuromorphicchiploihiusingthespikingneuralnetworksimulatorbrian
AT winfriedoed brian2loihianemulatorfortheneuromorphicchiploihiusingthespikingneuralnetworksimulatorbrian
AT christiantetzlaff brian2loihianemulatorfortheneuromorphicchiploihiusingthespikingneuralnetworksimulatorbrian
AT christiantetzlaff brian2loihianemulatorfortheneuromorphicchiploihiusingthespikingneuralnetworksimulatorbrian