TinyML for Ubiquitous Edge AI

TL;DR

TinyML enables deep learning on microcontrollers with ultra-low power, fostering ubiquitous edge AI applications without relying on cloud infrastructure.

Contribution

This paper discusses the challenges and technological enablers for deploying deep learning on resource-constrained embedded devices.

Findings

Addresses power-efficient neural network design for microcontrollers

Highlights hardware and software frameworks supporting TinyML

Envisions new edge AI applications independent of cloud services

Abstract

TinyML is a fast-growing multidisciplinary field at the intersection of machine learning, hardware, and software, that focuses on enabling deep learning algorithms on embedded (microcontroller powered) devices operating at extremely low power range (mW range and below). TinyML addresses the challenges in designing power-efficient, compact deep neural network models, supporting software framework, and embedded hardware that will enable a wide range of customized, ubiquitous inference applications on battery-operated, resource-constrained devices. In this report, we discuss the major challenges and technological enablers that direct this field's expansion. TinyML will open the door to the new types of edge services and applications that do not rely on cloud processing but thrive on distributed edge inference and autonomous reasoning.