A full on-device vision system trains a two-layer CNN with Adam optimization and runs inference at 6.3 FPS on a $15-40 ESP32 microcontroller using 1750 lines of self-contained C++.
TinyOL: TinyML with Online-Learning on Microcontrollers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
A survey of on-device learning in TinyML organized by distribution change regimes, highlighting influences on applications, hardware, and solutions plus a gap between benchmarks and deployments.
citing papers explorer
-
On-Device Vision Training, Deployment, and Inference on a Thumb-Sized Microcontroller
A full on-device vision system trains a two-layer CNN with Adam optimization and runs inference at 6.3 FPS on a $15-40 ESP32 microcontroller using 1750 lines of self-contained C++.
-
What changes after deployment? A survey on On-device Learning in TinyML
A survey of on-device learning in TinyML organized by distribution change regimes, highlighting influences on applications, hardware, and solutions plus a gap between benchmarks and deployments.