TinyML: AI on microcontrollers | Sri AI

Course overview

Machine learning in a few hundred kilobytes on ESP32 and Arduino: keyword spotting, gestures and fault detection running on a battery.

Level: Intermediate  ·  Mode: Weekend lab

Who this course is for

Embedded engineers and electronics students.

What you will learn

• Train models small enough for microcontrollers
• Deploy with TensorFlow Lite Micro
• Build keyword spotting and gesture sensing
• Run devices for months on a battery

Syllabus

1. Module 1: Why TinyML
2. Module 2: Data from sensors
3. Module 3: Training tiny models
4. Module 4: Quantisation for microcontrollers
5. Module 5: Deployment
6. Module 6: Power budgets

Final project

Every module ends in hands-on practice, and the course ends with a project you build and present. Your certificate names that project.

Before you start

Python for AI. Basic electronics helps.

Open-source tools you will use

• TFLite Micro
• ML Systems book (Harvard)

Draws on Harvard's open Machine Learning Systems textbook.