Machine Learning on Microcontrollers With Zephyr and Emlearn
summary
emlearn converts scikit‑learn or Keras models into efficient C99 code with a one‑liner model‑to‑C export and a header‑only C library that integrates as a Zephyr module; Zephyr provides sensor APIs, FIFO buffering and filesystems so embedded devices collect, label and run inference locally — example builds include an activity recognizer, a toothbrush timer and a cattle monitor that reports about 50x power savings versus raw data upload, with optional MicroPython bindings for rapid prototyping.
AI-written summary · about
chapters (13)
- 0:00Introduction to TinyML
- 1:32TinyML development challenges
- 5:22Activity recognition case study
- 9:46Sensor data acquisition
- 15:05Batch processing with RTIO
- 16:29Creating datasets
- 18:14Labeling data
- 21:14Training machine learning models
- 22:25Deploying models with emlearn
- 25:50MicroPython and C integration
- 28:42MicroPython ecosystem for ML
- 29:25Using emlearn in MicroPython
- 31:19Summary and Q&A
related talks
44mMachine Learning on Microcontrollers With Zephyr and Emlearn
27mMicrocontrollers and Machine Learning with MicroPython and emlearn
25mMachine Learning on Microcontrollers; Tiny, Useful and Fun
29mMicrocontrollers + Machine Learning with MicroPython in 1-2-3
36mTinyML at the Edge: Deploying and Optimizing AI Workloads on Zephyr RTOS
14mKeynote: Leveraging Zephyr and ML to Bring Smart Devices to Market, Faster
10mLightning Talk: Debugging Edge AI on Zephyr and Lessons Learned
26mNext generation machine learning for mobile and embedded platforms