0:00:00.890,0:00:06.330 The micro:bit machine learning tool lets you[br]train, test and improve a machine learning 0:00:06.330,0:00:10.219 model that can recognise different actions,[br]or movements. 0:00:10.219,0:00:13.330 Here’s a quick tour of how it works. 0:00:13.330,0:00:15.990 You’ll need two micro:bits. 0:00:15.990,0:00:19.610 You’ll hold or wear the first micro:bit. 0:00:19.610,0:00:27.250 Follow the instructions on screen for setting[br]up micro:bit 1. 0:00:27.250,0:00:30.369 Then unplug it and attach a battery pack. 0:00:30.369,0:00:37.460 If you have a wrist strap, you can attach[br]micro:bit 1 to your arm. 0:00:37.460,0:00:41.730 The second micro:bit stays connected to your[br]computer with a USB cable. 0:00:41.730,0:00:47.350 Follow the instructions on screen for setting[br]up micro:bit 2. 0:00:47.350,0:00:54.361 At the bottom of the screen you’ll see live[br]movement data from micro:bit 1’s[br]accelerometer sensor. 0:00:55.300,0:01:00.811 Each coloured line represents a different[br]direction, or dimension, you’re moving the micro:bit in. 0:01:02.449,0:01:05.519 Step 1, add some data! 0:01:05.519,0:01:10.159 Decide which actions you want the micro:bit[br]machine learning tool to recognise. 0:01:10.159,0:01:14.510 Clapping and waving are good ones to start[br]with. 0:01:14.510,0:01:18.750 Name your first action, then start moving! 0:01:18.750,0:01:26.479 Click the red button to collect your first[br]sample of data. 0:01:26.479,0:01:34.659 Collect at least three samples[br]of your first action. 0:01:34.659,0:01:43.649 And do the same for at least one other action. 0:01:43.649,0:01:46.190 Step 2, train the model. 0:01:46.190,0:01:51.560 This means that the machine learning tool[br]makes a set of rules to estimate which action 0:01:51.560,0:01:56.689 you’re doing when moving micro:bit 1. 0:01:56.689,0:01:59.840 Step 3, test the model. 0:01:59.840,0:02:02.290 Try making each of your actions. 0:02:02.290,0:02:07.640 The screen shows which action the model estimates[br]that you’re making. 0:02:07.640,0:02:14.310 The percentage number is how confident, or[br]sure, the model is. 0:02:14.310,0:02:20.513 Now try it yourself and see what different movements you can train the micro:bit machine learning tool to recognise.