Intelligence at the Extreme Edge: A Survey on Reformable TinyML
It addresses the challenge of making TinyML systems adaptable post-deployment for researchers and practitioners in edge computing, but is incremental as it surveys existing work.
This survey tackles the problem of enabling machine learning models to improve after deployment on energy-efficient microcontrollers, known as reformable TinyML, by proposing a novel taxonomy and analyzing deployment schemes, tools, and industrial impacts.
Tiny Machine Learning (TinyML) is an upsurging research field that proposes to democratize the use of Machine Learning and Deep Learning on highly energy-efficient frugal Microcontroller Units. Considering the general assumption that TinyML can only run inference, growing interest in the domain has led to work that makes them reformable, i.e., solutions that permit models to improve once deployed. This work presents a survey on reformable TinyML solutions with the proposal of a novel taxonomy. Here, the suitability of each hierarchical layer for reformability is discussed. Furthermore, we explore the workflow of TinyML and analyze the identified deployment schemes, available tools and the scarcely available benchmarking tools. Finally, we discuss how reformable TinyML can impact a few selected industrial areas and discuss the challenges and future directions.