Flexible design methodology for spike encoding implementation on FPGA
Spiking Neural Networks (SNNs) are promising candidates for low power and low latency embedded artificial intelligence, e.g., for edge computing. There is, however, a lack of naturally event-based sensors that could directly feed those networks, except for a few specialized flagship examples like ne...
Saved in:
Published in | 2022 IEEE Biomedical Circuits and Systems Conference (BioCAS) pp. 379 - 383 |
---|---|
Main Authors | , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
13.10.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Spiking Neural Networks (SNNs) are promising candidates for low power and low latency embedded artificial intelligence, e.g., for edge computing. There is, however, a lack of naturally event-based sensors that could directly feed those networks, except for a few specialized flagship examples like neuromorphic retinas. Using conventional sensors in conjunction with SNNs requires to encode their outputs into spikes, which can be detrimental to energy consumption or latency when performed in software. Spike-encoding algorithms have been studied within specific contexts in the literature but are often limited to a software implementation. Here we introduce a flexible design methodology for implementing a generalized version of such a spike-encoder on Field Programmable Gate Array (FPGA). Our approach relies on High-Level Synthesis, which allows to quickly evaluate different hardware architectures to tailor the solution to the application needs. This work could accelerate the development of lower power and lower latency smart sensors by combining conventional, possibly off-the-shelf, sensors with hardware SNNs. |
---|---|
AbstractList | Spiking Neural Networks (SNNs) are promising candidates for low power and low latency embedded artificial intelligence, e.g., for edge computing. There is, however, a lack of naturally event-based sensors that could directly feed those networks, except for a few specialized flagship examples like neuromorphic retinas. Using conventional sensors in conjunction with SNNs requires to encode their outputs into spikes, which can be detrimental to energy consumption or latency when performed in software. Spike-encoding algorithms have been studied within specific contexts in the literature but are often limited to a software implementation. Here we introduce a flexible design methodology for implementing a generalized version of such a spike-encoder on Field Programmable Gate Array (FPGA). Our approach relies on High-Level Synthesis, which allows to quickly evaluate different hardware architectures to tailor the solution to the application needs. This work could accelerate the development of lower power and lower latency smart sensors by combining conventional, possibly off-the-shelf, sensors with hardware SNNs. |
Author | Saighi, Sylvain Gillet, Clemence Le Gal, Bertrand Vincent, Adrien F. |
Author_xml | – sequence: 1 givenname: Clemence surname: Gillet fullname: Gillet, Clemence email: clemence.gillet@ims-bordeaux.fr organization: Univ. Bordeaux, Bordeaux INP, CNRS,Laboratoire de L'Intégration du Matériau au Système,Talence,France – sequence: 2 givenname: Adrien F. surname: Vincent fullname: Vincent, Adrien F. email: adrien.vincent@ims-bordeaux.fr organization: Univ. Bordeaux, Bordeaux INP, CNRS,Laboratoire de L'Intégration du Matériau au Système,Talence,France – sequence: 3 givenname: Bertrand surname: Le Gal fullname: Le Gal, Bertrand email: bertrand.legal@ims-bordeaux.fr organization: Univ. Bordeaux, Bordeaux INP, CNRS,Laboratoire de L'Intégration du Matériau au Système,Talence,France – sequence: 4 givenname: Sylvain surname: Saighi fullname: Saighi, Sylvain email: sylvain.saighi@ims-bordeaux.fr organization: Univ. Bordeaux, Bordeaux INP, CNRS,Laboratoire de L'Intégration du Matériau au Système,Talence,France |
BookMark | eNotj81KxDAYACPowV19Ai95gdb8_xxr2a7CgoIK3pak-doNtklpe3DfXsGFgbkNzAZdp5wAIUxJSSmxj08x19W7FJbIkhHGSmuFUYReoQ1VSgplqf66RbtmgJ_oB8ABltgnPMJ6yiEPuT_jLs94meI3YEhtDjH1OI7TACOk1a0xJ_xH87av7tBN54YF7i_eos9m91E_F4fX_UtdHYoTlWwtWidUALDGECVDZ7S1joIPygRgVraB67bV2gvlDQ_UCM8lo1Y6xkEHafkWPfx3IwAcpzmObj4fL2f8FxfDSfg |
ContentType | Conference Proceeding |
DBID | 6IE 6IL CBEJK RIE RIL |
DOI | 10.1109/BioCAS54905.2022.9948601 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library (IEL) IEEE Proceedings Order Plans (POP All) 1998-Present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
EISBN | 166546917X 9781665469173 |
EndPage | 383 |
ExternalDocumentID | 9948601 |
Genre | orig-research |
GroupedDBID | 6IE 6IL CBEJK RIE RIL |
ID | FETCH-LOGICAL-h152t-ca46dee988065df8799a1ebd68de295cd37cc77b46b83d184b352195a23e7d593 |
IEDL.DBID | RIE |
IngestDate | Thu Jan 18 11:14:53 EST 2024 |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-h152t-ca46dee988065df8799a1ebd68de295cd37cc77b46b83d184b352195a23e7d593 |
PageCount | 5 |
ParticipantIDs | ieee_primary_9948601 |
PublicationCentury | 2000 |
PublicationDate | 2022-Oct.-13 |
PublicationDateYYYYMMDD | 2022-10-13 |
PublicationDate_xml | – month: 10 year: 2022 text: 2022-Oct.-13 day: 13 |
PublicationDecade | 2020 |
PublicationTitle | 2022 IEEE Biomedical Circuits and Systems Conference (BioCAS) |
PublicationTitleAbbrev | BioCAS |
PublicationYear | 2022 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
Score | 1.8634589 |
Snippet | Spiking Neural Networks (SNNs) are promising candidates for low power and low latency embedded artificial intelligence, e.g., for edge computing. There is,... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 379 |
SubjectTerms | Computer architecture data encoding Design methodology edge computing Encoding Energy consumption Hardware high level synthesis Software Software algorithms spike sorting Spiking neural networks |
Title | Flexible design methodology for spike encoding implementation on FPGA |
URI | https://ieeexplore.ieee.org/document/9948601 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LSwMxEA61J08qrfgmB49mu7t5bY61dC1CpaCF3koeUyzVtuj24q83ybaK4kHIIYQNu8nATr7MN98gdB20JaWZaWI9_iGMMkGUpZbIYpZBSAtRMWI6fBCDMbuf8EkD3XzlwgBAJJ9BEroxlu9WdhOuyjpKhZJJHuvsFWle52rtyDmp6tzOV73uo8c7Kfe4L8-T7eM_6qZEt1EeoOHuhTVbZJFsKpPYj19ajP_9okPU_k7Qw6Mv13OEGrBsoX4ZxC3NC2AXaRm4rg4d782xP5vi9_V8ATgoV4ZZeP66444H42DfytFdt43GZf-pNyDbKgnk2fveiljNhANQRQiRulkhldIZGCcKB7ni1lFprZSGCVNQ5wGd8WeuTHGdU5COK3qMmsvVEk4QBi3A5bllwCxLtVVCChDGSpdy7Tg9Ra2wBdN1LYQx3a7-7O_hc7QfzBB-9Bm9QM3qbQOX3oNX5iqa7hPr_Z1Q |
link.rule.ids | 310,311,786,790,795,796,802,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PT8IwFG6IHvSkBoy_7cGjG9v6az0iYaICIRESbmRtH5GgQHRc_OttO8BoPJjs0Cxpuu0l-_r1fe97CN04b0mhJnmgLf8JKKE8kJroQKSTGFxZiPQZ026Pt4f0ccRGFXS7rYUBAC8-g9ANfS7fLPTKHZXVpXQtkyzX2bU4H4myWmsjz4lk_W66aDaeLeOJmGV-SRKuJ_zonOKBIztA3c2SpV5kFq4KFerPX26M_32mQ1T7LtHD_S34HKEKzKuolTl7S_UK2HhhBi77Q_uTc2x3p_hjOZ0Bdt6Vbhaevm3U4y482F5Z_75RQ8OsNWi2g3WfhODFom8R6JxyAyBTlyQ1k1RImcegDE8NJJJpQ4TWQijKVUqMpXTK7rpiyfKEgDBMkmO0M1_M4QRhyDmYJNEUqKZRriUXHLjSwkQsN4ycoqr7BONlaYUxXr_92d-3r9Fee9DtjDsPvadztO9C4n77MblAO8X7Ci4tnhfqyofxC2SzoKQ |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2022+IEEE+Biomedical+Circuits+and+Systems+Conference+%28BioCAS%29&rft.atitle=Flexible+design+methodology+for+spike+encoding+implementation+on+FPGA&rft.au=Gillet%2C+Clemence&rft.au=Vincent%2C+Adrien+F.&rft.au=Le+Gal%2C+Bertrand&rft.au=Saighi%2C+Sylvain&rft.date=2022-10-13&rft.pub=IEEE&rft.spage=379&rft.epage=383&rft_id=info:doi/10.1109%2FBioCAS54905.2022.9948601&rft.externalDocID=9948601 |