WEBVTT 00:00:00.890 --> 00:00:06.330 The micro:bit machine learning tool lets you train, test and improve a machine learning 00:00:06.330 --> 00:00:10.219 model that can recognise different actions, or movements. 00:00:10.219 --> 00:00:13.330 Here’s a quick tour of how it works. 00:00:13.330 --> 00:00:15.990 You’ll need two micro:bits. 00:00:15.990 --> 00:00:19.610 You’ll hold or wear the first micro:bit. 00:00:19.610 --> 00:00:27.250 Follow the instructions on screen for setting up micro:bit 1. 00:00:27.250 --> 00:00:30.369 Then unplug it and attach a battery pack. 00:00:30.369 --> 00:00:37.460 If you have a wrist strap, you can attach micro:bit 1 to your arm. 00:00:37.460 --> 00:00:41.730 The second micro:bit stays connected to your computer with a USB cable. 00:00:41.730 --> 00:00:47.350 Follow the instructions on screen for setting up micro:bit 2. 00:00:47.350 --> 00:00:54.361 At the bottom of the screen you’ll see live movement data from micro:bit 1’s accelerometer sensor. 00:00:55.300 --> 00:01:00.811 Each coloured line represents a different direction, or dimension, you’re moving the micro:bit in. 00:01:02.449 --> 00:01:05.519 Step 1, add some data! 00:01:05.519 --> 00:01:10.159 Decide which actions you want the micro:bit machine learning tool to recognise. 00:01:10.159 --> 00:01:14.510 Clapping and waving are good ones to start with. 00:01:14.510 --> 00:01:18.750 Name your first action, then start moving! 00:01:18.750 --> 00:01:26.479 Click the red button to collect your first sample of data. 00:01:26.479 --> 00:01:34.659 Collect at least three samples of your first action. 00:01:34.659 --> 00:01:43.649 And do the same for at least one other action. 00:01:43.649 --> 00:01:46.190 Step 2, train the model. 00:01:46.190 --> 00:01:51.560 This means that the machine learning tool makes a set of rules to estimate which action 00:01:51.560 --> 00:01:56.689 you’re doing when moving micro:bit 1. 00:01:56.689 --> 00:01:59.840 Step 3, test the model. 00:01:59.840 --> 00:02:02.290 Try making each of your actions. 00:02:02.290 --> 00:02:07.640 The screen shows which action the model estimates that you’re making. 00:02:07.640 --> 00:02:14.310 The percentage number is how confident, or sure, the model is. 00:02:14.310 --> 00:02:20.513 Now try it yourself and see what different movements you can train the micro:bit machine learning tool to recognise.