TinyML Application Development for Everyone

Hands-on workshop at Arm AIoT Dev Summit December 2019

In this tutorial we will teach a board to recognise gestures! We'll capture motion data from the Arduino Nano 33 BLE Sense board, import it into TensorFlow to train a model, and deploy a classifier onto the board using TensorFlow Lite for microcontrollers.

Exercises

• Introduction
• Exercise 1: Development Environment
• Exercise 2: Source Code
• Exercise 3: Hardware
• Exercise 4: Visualizing the IMU Data
• Exercise 5: Gather the Training Data
• Exercise 6: Machine Learning
• Exercise 7: Classifying IMU Data
• Exercise 8: Emojis
• Exercise 9: Gesture Controlled USB Emoji Keyboard
• Exercise 10: Next Steps