A neural network framework for small microcontrollers

By: Contributor(s): Material type: ArticleArticleDescription: 1 archivo (265,3 kB)Subject(s): Online resources: Summary: This 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.
Star ratings
    Average rating: 0.0 (0 votes)

Formato de archivo PDF. -- Este documento es producción intelectual de la Facultad de Informática - UNLP (Colección BIPA/Biblioteca)

This 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.

Congreso Argentino de Ciencias de la Computación (27mo : 2021 : Salta, Argentina)