0:00:00.840,0:00:03.199
the microbit machine learning tool lets

0:00:03.199,0:00:05.960
you train test and improve a machine

0:00:05.960,0:00:07.879
learning model that can recognize

0:00:07.879,0:00:09.960
different actions or

0:00:09.960,0:00:13.040
movements here's a quick tour of how it

0:00:13.040,0:00:16.880
works you'll need two microbits you'll

0:00:16.880,0:00:19.240
hold or wear the first

0:00:19.240,0:00:21.439
microbit follow the instructions on

0:00:21.439,0:00:25.400
screen for setting up microbit

0:00:26.080,0:00:29.279
one then unplug it and attach a battery

0:00:29.279,0:00:31.960
pack if you have a wrist strap you can

0:00:31.960,0:00:35.480
attach microbit one to your

0:00:36.480,0:00:39.360
arm the second microbit stays connected

0:00:39.360,0:00:42.360
to your computer with a USB cable follow

0:00:42.360,0:00:44.200
the instructions on screen for setting

0:00:44.200,0:00:47.000
up microbit

0:00:47.559,0:00:50.239
2 at the bottom of the screen you'll see

0:00:50.239,0:00:52.840
live movement data from microbit 1's

0:00:52.840,0:00:54.280
accelerometer

0:00:54.280,0:00:57.120
sensor each colored line represents a

0:00:57.120,0:00:59.440
different direction or Dimension you're

0:00:59.440,0:01:01.399
moving the microbit

0:01:01.399,0:01:04.560
in Step One add some

0:01:04.560,0:01:07.320
data decide which actions you want the

0:01:07.320,0:01:09.000
microbit machine learning tool to

0:01:09.000,0:01:12.119
recognize clapping and waving are good

0:01:12.119,0:01:13.479
ones to start

0:01:13.479,0:01:17.560
with name your first action then start

0:01:17.560,0:01:20.159
moving click the red button to collect

0:01:20.159,0:01:23.159
your first sample of

0:01:25.079,0:01:28.520
data collect at least three samples of

0:01:28.520,0:01:31.840
your first action

0:01:34.399,0:01:38.680
and do the same for at least one other

0:01:42.600,0:01:46.320
action step two train the model this

0:01:46.320,0:01:48.159
means that the machine learning tool

0:01:48.159,0:01:51.040
makes a set of rules to estimate which

0:01:51.040,0:01:55.360
action you're doing when moving microbit

0:01:55.640,0:02:00.399
one step three test the model try making

0:02:00.399,0:02:03.799
each of your actions the screen shows

0:02:03.799,0:02:06.039
which action the model estimates that

0:02:06.039,0:02:09.200
you're making the percentage number is

0:02:09.200,0:02:13.319
how confident or sure the model

0:02:13.319,0:02:16.280
is now try it yourself and see what

0:02:16.280,0:02:17.959
different movements you can train the

0:02:17.959,0:02:20.800
microbit machine learning tool to

0:02:20.800,0:02:23.800
recognize