Mostrar el registro sencillo del ítem
Flexible design methodology for spike encoding implementation on FPGA
dc.rights.license | open | en_US |
hal.structure.identifier | Laboratoire de l'intégration, du matériau au système [IMS] | |
dc.contributor.author | GILLET, Clemence | |
hal.structure.identifier | Laboratoire de l'intégration, du matériau au système [IMS] | |
dc.contributor.author | VINCENT, Adrien F. | |
hal.structure.identifier | Laboratoire de l'intégration, du matériau au système [IMS] | |
dc.contributor.author | LE GAL, Bertrand | |
hal.structure.identifier | Laboratoire de l'intégration, du matériau au système [IMS] | |
dc.contributor.author | SAÏGHI, Sylvain | |
dc.date.accessioned | 2024-05-07T11:28:13Z | |
dc.date.available | 2024-05-07T11:28:13Z | |
dc.date.issued | 2022-10 | |
dc.date.conference | 2022-10-13 | |
dc.identifier.issn | 2473-2001 | en_US |
dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/199699 | |
dc.description.abstractEn | 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. | |
dc.language.iso | EN | en_US |
dc.subject | Energy consumption | |
dc.subject | Design methodology | |
dc.subject | Software algorithms | |
dc.subject | Computer architecture | |
dc.subject | Hardware | |
dc.subject | Software | |
dc.subject | Encoding | |
dc.subject | Spiking neural networks | |
dc.subject | Data encoding | |
dc.subject | High level synthesis | |
dc.subject | Spike sorting | |
dc.subject | Edge computing | |
dc.title.en | Flexible design methodology for spike encoding implementation on FPGA | |
dc.type | Communication dans un congrès | en_US |
dc.identifier.doi | 10.1109/BioCAS54905.2022.9948601 | en_US |
dc.subject.hal | Sciences de l'ingénieur [physics] | en_US |
bordeaux.page | 379-383 | en_US |
bordeaux.hal.laboratories | IMS : Laboratoire de l'Intégration du Matériau au Système - UMR 5218 | en_US |
bordeaux.institution | Université de Bordeaux | en_US |
bordeaux.institution | Bordeaux INP | en_US |
bordeaux.institution | CNRS | en_US |
bordeaux.conference.title | 2022 IEEE Biomedical Circuits and Systems Conference (BioCAS) | en_US |
bordeaux.country | tw | en_US |
bordeaux.title.proceeding | 2022 IEEE Biomedical Circuits and Systems Conference (BioCAS) | en_US |
bordeaux.team | BIOELECTRONICS-IA | en_US |
bordeaux.team | CIRCUIT DESIGN-CSN | en_US |
bordeaux.conference.city | Taipei | en_US |
hal.identifier | hal-04570859 | |
hal.version | 1 | |
hal.date.transferred | 2024-05-07T11:28:15Z | |
hal.invited | oui | en_US |
hal.proceedings | oui | en_US |
hal.conference.end | 2022-10-15 | |
hal.popular | non | en_US |
hal.audience | Internationale | en_US |
hal.export | true | |
dc.rights.cc | Pas de Licence CC | en_US |
bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2022-10&rft.spage=379-383&rft.epage=379-383&rft.eissn=2473-2001&rft.issn=2473-2001&rft.au=GILLET,%20Clemence&VINCENT,%20Adrien%20F.&LE%20GAL,%20Bertrand&SA%C3%8FGHI,%20Sylvain&rft.genre=unknown |
Archivos en el ítem
Archivos | Tamaño | Formato | Ver |
---|---|---|---|
No hay archivos asociados a este ítem. |