TinyML for Ubiquitous Edge AI
This work addresses the problem of deploying AI on resource-constrained edge devices for applications requiring distributed and autonomous processing, but it is incremental as it reviews existing challenges and enablers without introducing new methods.
The paper tackles the challenge of enabling deep learning on low-power embedded devices by addressing power-efficient models, software frameworks, and hardware, aiming to support ubiquitous inference applications without cloud reliance.
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.