dc.creator | Yousefzadeh, Amirreza | es |
dc.creator | Khoei, Mina A. | es |
dc.creator | Hosseini, Sahar | es |
dc.creator | Holanda, Priscila | es |
dc.creator | Leroux, Sam | es |
dc.creator | Moreira, Orlando | es |
dc.creator | Tapson, Jonathan | es |
dc.creator | Dhoedt, Bart | es |
dc.creator | Simoens, Pieter | es |
dc.creator | Serrano Gotarredona, María Teresa | es |
dc.creator | Linares Barranco, Bernabé | es |
dc.date.accessioned | 2020-06-02T11:56:57Z | |
dc.date.available | 2020-06-02T11:56:57Z | |
dc.date.issued | 2019 | |
dc.identifier.citation | Yousefzadeh, A., Khoei, M.A., Hosseini, S., Holanda, P., Leroux, S., Moreira, O.,...,Linares Barranco, B. (2019). Asynchronous Spiking Neurons, the Natural Key to Exploit Temporal Sparsity. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 9 (4), 668-678. | |
dc.identifier.issn | 2156-3357 | es |
dc.identifier.issn | 2156-3365 | es |
dc.identifier.uri | https://hdl.handle.net/11441/97361 | |
dc.description.abstract | Inference of Deep Neural Networks for stream signal
(Video/Audio) processing in edge devices is still challenging.
Unlike the most state of the art inference engines which are
efficient for static signals, our brain is optimized for real-time
dynamic signal processing. We believe one important feature of
the brain (asynchronous state-full processing) is the key to its
excellence in this domain. In this work, we show how asynchronous
processing with state-full neurons allows exploitation of
the existing sparsity in natural signals. This paper explains three
different types of sparsity and proposes an inference algorithm
which exploits all types of sparsities in the execution of already
trained networks. Our experiments in three different applications
(Handwritten digit recognition, Autonomous Steering and Hand-
Gesture recognition) show that this model of inference reduces
the number of required operations for sparse input data by a
factor of one to two orders of magnitudes. Additionally, due to
fully asynchronous processing this type of inference can be run on
fully distributed and scalable neuromorphic hardware platforms. | es |
dc.description.sponsorship | EU H2020 grants 687299 ”NEURAM3” | es |
dc.description.sponsorship | EU H2020 grants 824164 ”HERMES” | es |
dc.description.sponsorship | Ministry of Economy and Competitivity (Spain) TEC2015- 63884-C2-1-P (COGNET) | es |
dc.format | application/pdf | es |
dc.format.extent | 11 p. | es |
dc.language.iso | eng | es |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | es |
dc.relation.ispartof | IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 9 (4), 668-678. | |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.title | Asynchronous Spiking Neurons, the Natural Key to Exploit Temporal Sparsity | es |
dc.type | info:eu-repo/semantics/article | es |
dcterms.identifier | https://ror.org/03yxnpp24 | |
dc.type.version | info:eu-repo/semantics/submittedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Arquitectura y Tecnología de Computadores | es |
dc.relation.projectID | 687299 ”NEURAM3” | es |
dc.relation.projectID | 824164 ”HERMES” | es |
dc.relation.projectID | TEC2015- 63884-C2-1-P (COGNET) | es |
dc.relation.publisherversion | https://ieeexplore.ieee.org/document/8890681 | es |
dc.identifier.doi | 10.1109/JETCAS.2019.2951121 | es |
dc.contributor.group | Universidad de Sevilla. TIC178: Diseño y Test de Circuitos Integrados de Señal Mixta | es |
idus.validador.nota | Preprint | es |
dc.journaltitle | IEEE Journal on Emerging and Selected Topics in Circuits and Systems | es |
dc.publication.volumen | 9 | es |
dc.publication.issue | 4 | es |
dc.publication.initialPage | 668 | es |
dc.publication.endPage | 678 | es |