In this video, the robot begins with a random 2x2 neural network for
controlling the motors based on the values of two light sensors
mounted on the front. A supervised learning algorithm (delta rule) is
used to train the network by using a known solution as a teacher 5
times per second. At the beginning of the video, you can see that the
robot turns away from the light and even goes backward. However,
within 10-15 seconds, the network is already trained sufficiently to
follow the light beam.