Estrebou, César Armando

MbedML : a machine learning project for embedded systems - 1 archivo (776,0 kB)

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

This article describes the tasks being carried out within the framework of a research and development project on machine learning techniques and algorithms applied to small devices. It includes a brief review of the available technologies, online development platforms, work methodology and open source software for the implementation of solutions. Experiments carried out on a proper implementation of an inference algorithm for convolutional neural networks are also presented with interesting preliminary results regarding existing implementations.



DIF-M8326


APRENDIZAJE AUTOMÁTICO
INTERNET DE LAS COSAS
SISTEMAS EMBEBIDOS