In this unit, supervised learning method will be introduced.

We also do an activity that will train the AI robot to participate in a race.  The robot is trained to go inside the arena in circles along the walls.  In this training, you will practice supervised learning. 

Supervised learning is the most popular AI learning method.  It works very well together with artificial neuron network.

The core concept of supervised learning is imitation. Supervised learning has 2 stages.

The first stage is called Training.  In the training stage, robot imitated what the trainer decided.  Training data is used to teach the robot.  For example, a set of images as input will be shown to the robot, and the actions (decisions correspond to the input images) will be chosen.  Through this training process, the artificial neural network was modified so that it became capable of mimicking the same decision making.

The second stage is called Testing (or Usage).  In this stage, the robot is able to make good decisions on new images.

In summary:

1. AI requires training.
2. Supervised learning is a learning method which is used to train AI.
3. Supervised learning requires training data.
4. Training data has input and the corresponding labeled output.
5. Through showing the input and output, the machine can learn to imitate the decision of the trainer.
6. To achieve good quality AI, the amount and accuracy of training data are very important.

Material:

The Robo Race arena has 4 walls with red color.  A black wall is placed in the middle of the arena to create a circle (oval) race course.

Use demo parameters "Robot Race" as below

Switch on and connect the robot to your PC.  Press the <Connection> button.

With the the AI parameters set up correctly, the following neural network will be shown.

Self explanatory

- click the <reset learning> button once

- off the <self drive> button

- click the <learning> button

- put the robot on the start line

- while watching the robot, click the arrows on the right hand side of the screen to move the robot.

- firstly, click the "go forward" arrow to move the robot

- make the robot going in the race course

- repeat the above steps for 2 to 3 circles.  Go to Testing the result.

**you can re-do the training several times trying to handle more situations the robot may encounter.  For example, hitting the walls or going into corners.  More training will make the robot more clever.

- Off the <learning> button.  Click the <self drive> button.  The robot will used the learned intelligence to move around.

- test whether the robot is ready for the race.

- start the race with 2 to 3 robots running together.

Can the robot race?  Why it can?

What are the inputs?  How many inputs have you used?

What are the outputs?  How many outputs are there in the Robo Race.

Has learning been achieved?  Has the robot gained intelligence after training?

Discuss the concept of supervised learning.