A web page and a micro:bit talk over USB and radio. Graph a micro:bit's sensors, send it commands, relay messages by radio, train models on photos and on movements, and finish with an AI sorter of your own.
★ Challenge completeThe micro:bit sends readings to the computer as lines of text, and the computer sends it commands.
A micro:bit sends each sensor reading down the USB cable as a line of text, such as light:128. The computer turns the stream of lines into a graph.
The computer can send lines of text too. The micro:bit reads each whole line and its program decides what the word means, so both sides must agree on every word.
A micro:bit on the cable relays messages by radio, so the micro:bit doing the work can be anywhere in the room.
A micro:bit on the cable relays messages by radio, so the micro:bit doing the work can be anywhere in the room. The bridge passes radio to serial one way and serial to radio the other.
Train a model in Teachable Machine, test it on photos it has never seen, then send its labels to a micro:bit.
Train an image model in Teachable Machine, then test it on photos it has never seen. It works on photos like its training photos and fails on others, so to fix a model you change its data.
The board sends your model's label down the USB cable as a line of text. The micro:bit's program decides what each label does, and must also handle labels it doesn't expect.
Train a model on movements with micro:bit CreateAI; it runs on the micro:bit itself, and the Machine Learning blocks act on what it recognises.
A movement is a short recording of x, y and z acceleration. micro:bit CreateAI learns the shape of those recordings from your samples, so it tells movements apart by how they move, and the model then runs on the micro:bit itself.
The Machine Learning blocks run code when the model's estimated action changes. on ML start runs once when an action begins, not again while it carries on, and unknown means no action is sure enough.
Choose a sorting problem, build a fair test set, train and improve a model, connect a micro:bit build, and report its limits.
Choose a sorting problem, build a fair test set first, train and improve a Teachable Machine model until every group passes, connect a micro:bit build that acts safely on its labels, and report what it still gets wrong.
Progress is saved in this browser only. Nothing is sent anywhere.
For teachers: Teacher guide (notes, answers, solutions, slides and worksheets)