Microcontrollers + Machine Learning with MicroPython in 1-2-3
summary
MicroPython runs on tiny hardware (less than 1 MB RAM) and on an ESP32S3 ($2.5 chip, ~$6 board) that boots a Python prompt in ~30 seconds; examples show a Wi‑Fi + MQTT temperature sensor using asyncio, real‑time audio at 16,000 samples/sec handled by C modules, and an activity tracker that trains with scikit‑learn in under 20 seconds and loads a converted random‑forest CSV into emarn MicroPython native C modules, giving ~10× speed and size improvements.
AI-written summary · about
chapters (16)
- 0:00Introduction
- 1:55Goal
- 2:38What is a microcontroller
- 4:04Why MicroPython
- 5:06Setup with Viper IDE
- 6:52Temperature sensor
- 8:37Third-party libraries
- 10:23Advanced use cases
- 11:51Audio processing with C
- 14:01Extending with C modules
- 15:46Native modules
- 16:28Digital signal processing for sound
- 17:11Machine learning on microcontrollers
- 20:44Training and deploying ML
- 23:35Summary
- 26:02Q&A
related talks
27mMicrocontrollers and Machine Learning with MicroPython and emlearn
25mMachine Learning on Microcontrollers; Tiny, Useful and Fun
32mNext level Machine Learning with TinyML and Python
01h 53mTinyML: Machine Learning’s Future is Tiny and Bright
28mMicrocontrollers (MCUs), Cloud, and a Chance of AI with Tara Walker
44mMachine Learning on Microcontrollers With Zephyr and Emlearn
31mKeynote: The next big thing in machine learning is tiny
19mWhy Machine Learning on Microcontrollers?