Artificial Intelligence Experiment #15
NextPreviousReset Experiment Start Learning Hide Labels Hide Wires X-Ray Wires
Output 1 Output 2 Output 3 Output 4
Artificial Intelligence Introduction: Personalised Home Automation with AI

In this experiment, we build a simple home automation system that can do any four different things at our command.

← In the table on the left, you see four outputs, labelled Output 1 to 4. You can edit the labels. For example, instead of 'Output 1', you could write 'Lights on' or 'Washing Machine on'.

Enter up to three training commands in each of the four outputs.The idea is that a command, such as 'switch lights on' turns on the lights. 'switch lights off' turns them off, etc. Observe how the AI configures its input perceptrons as you enter training data into the table. Should you need some inspiration, take a look at the table below.

Lights on Lights off Fan on Fan off
switch light on switch light off switch fan on switch fan off
lights on lights off fan on fan off
too dark too bright too warm too cold

Before a neural network can make decisions, it has to be trained. Let's start the training process. Click on the 'Start Learning' button at the bottom to train the network. Adjust the speed with the slider at the bottom of the window.

Once learning is complete, enter a command in the bar at the bottom. Uses some of the words in your table. For example, 'fan lights off'. Observe how the ANN uses keywords as input and proposes a possible classification into any of the four output classes.

Try a few other combinations of words. Document each experiment on a sheet of paper, together with the classification that the AI proposes.

This scenario has been inspired by and developed in cooperation between the Digital Technologies Institute, Australia,Apps For Good, United Kingdom,and the Digital Technologies Hub, Australia

This text is displayed if your browser does not support HTML5 Canvas.
Training Cycles