A Neural Network Framework for Small Microcontrollers

dc.creatorEstrebou, César Armando
dc.creatorFleming, Martín
dc.creatorSaavedra, Marcos David
dc.creatorAdra, Federico
dc.date2021-10
dc.date2021
dc.date2022-02-02T15:44:48Z
dc.date.accessioned2023-07-15T05:21:56Z
dc.date.available2023-07-15T05:21:56Z
dc.identifierhttp://sedici.unlp.edu.ar/handle/10915/130315
dc.identifierisbn:978-987-633-574-4
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/7473086
dc.descriptionThis paper presents a lightweight and compact library designed to perform convolutional neural network inference for microcontrollers with severe hardware limitations. A review of similar open source libraries is included and an experiment is developed to compare their performance on different microcontrollers. The proposed library shows at least a 9 times improvement over the implementation of Google Tensorflow Lite with respect to memory usage and inference time.
dc.descriptionWorkshop: WASI – Agentes y Sistemas Inteligentes
dc.descriptionRed de Universidades con Carreras en Informática
dc.formatapplication/pdf
dc.format51-60
dc.languageen
dc.rightshttp://creativecommons.org/licenses/by-nc-sa/4.0/
dc.rightsCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.subjectCiencias Informáticas
dc.subjectMachine learning
dc.subjectConvolutional Neural Networks
dc.subjectMicrocontrollers
dc.subjectFrameworks
dc.subjectTinyML
dc.titleA Neural Network Framework for Small Microcontrollers
dc.typeObjeto de conferencia
dc.typeObjeto de conferencia


Este ítem pertenece a la siguiente institución