Show simple item record

dc.contributor.authorMonfort Grau, Marc
dc.contributor.authorPueyo Centelles, Roger
dc.contributor.authorFreitag, Fèlix
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Arquitectura de Computadors
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors
dc.date.accessioned2021-11-16T09:57:14Z
dc.date.available2021-11-16T09:57:14Z
dc.date.issued2021
dc.identifier.citationMonfort, M.; Pueyo, R.; Freitag, F. On-device training of machine learning models on microcontrollers with a look at federated learning. A: ACM International Conference on Information Technology for Social Good. "GoodIT'21: proceedings of the 2021 Conference on Information Technology for Social Good: September 9–11, 2021, Roma, Italy". New York: Association for Computing Machinery (ACM), 2021, p. 198-203. ISBN 978-1-4503-8478-0. DOI 10.1145/3462203.3475896.
dc.identifier.isbn978-1-4503-8478-0
dc.identifier.urihttp://hdl.handle.net/2117/356500
dc.description.abstractRecent progress in machine learning frameworks makes it now possible to run an inference with sophisticated machine learning models on tiny microcontrollers. Model training, however, is typically done separately on powerful computers. There, the training process has abundant CPU and memory resources to process the stored datasets. In this work, we explore a different approach: training the model directly on the microcontroller. We implement this approach for a keyword spotting task. Then, we extend the training process using federated learning among microcontrollers. Our experiments with model training show an overall trend of decreasing loss with the increase of training epochs.
dc.description.sponsorshipThis work was partially funded by the Spanish Government under contracts PID2019-106774RB-C21, PCI2019-111850-2 (DiPET CHIST-ERA), PCI2019-111851-2 (LeadingEdge CHIST-ERA), and the Generalitat de Catalunya as Consolidated Research Group 2017- SGR-990.
dc.format.extent6 p.
dc.language.isoeng
dc.publisherAssociation for Computing Machinery (ACM)
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subject.lcshMachine learning
dc.subject.lcshEmbedded computer systems
dc.subject.lcshMicrocontrollers
dc.subject.otherKeyword spotting
dc.subject.otherEmbedded systems
dc.subject.otherFederated learning
dc.titleOn-device training of machine learning models on microcontrollers with a look at federated learning
dc.typeConference report
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacOrdinadors immersos, Sistemes d'
dc.subject.lemacMicrocontroladors
dc.contributor.groupUniversitat Politècnica de Catalunya. CNDS - Xarxes de Computadors i Sistemes Distribuïts
dc.identifier.doi10.1145/3462203.3475896
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://dl.acm.org/doi/10.1145/3462203.3475896
dc.rights.accessOpen Access
local.identifier.drac32221135
dc.description.versionPostprint (author's final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/AEI/2PE/PID2019-106774RB-C21
dc.relation.projectidinfo:eu-repo/grantAgreement/AEI/2PE/PCI2019-111850-2
dc.relation.projectidinfo:eu-repo/grantAgreement/AEI/2PE/PCI2019-111851-2
dc.relation.projectidinfo:eu-repo/grantAgreement/AGAUR/2017 SGR 990
local.citation.authorMonfort, M.; Pueyo, R.; Freitag, F.
local.citation.contributorACM International Conference on Information Technology for Social Good
local.citation.pubplaceNew York
local.citation.publicationNameGoodIT’21: proceedings of the 2021 Conference on Information Technology for Social Good: September 9–11, 2021, Roma, Italy
local.citation.startingPage198
local.citation.endingPage203


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder