TensorFlow has already made it possible to use trained machine learning models on smartphones. TensorFlow Lite goes one step further and runs TensorFlow models on a Raspberry Pi. uTensor even puts AI on a microcontroller (MCU). They are small and cheap, but they are also energy efficient, slow, and have little RAM, which doesn’t make it any easier. In my presentation I analyze meaningful use cases, possibilities, and ideas for machine learning on embedded devices. I’ll also show some examples and live demos.