TinyML: A Systematic Review and Synthesis of Existing Research

Tiny Machine Learning (TinyML), a rapidly evolving edge computing concept that links embedded systems (hardware and software) and machine learning, with the purpose of realizing ultra-low-power and low-cost and efficiency and privacy, brings machine learning inference to battery-powered intelligent devices. In this study, we conduct a systematic review of TinyML research by synthesizing 47 papers from academic and grey publication since 2019 (the early TinyML publication starts from 2019). Relevant TinyML literature is analyzed from five aspects: hardware, framework, datasets, use cases, and algorithms/model. This systematic review will serve as a roadmap for understanding the literature within the new emerging field of TinyML.