The effectiveness of a neural network heavily depends on its learning data. Let's explore data bias and how to avoid it.

In this experiment, we train the neural network with black shapes on a white background. Scroll through the shapes and take a look. Then, start the learning process. Hint: Press on the Hide Wires button to make the learning process faster.

Once learning is complete, drag the pattern slider under the letter. You will first see the black shapes on white background (the learning data) and then the same shapes, but white on a black background. Does our ANN recognize the white shapes?

The ANN has only learned to recognise black shapes on a white background. It struggles to recognize the inverse (black and white swapped) shapes. Our network has a data bias.

To avoid data bias, it is important to provide the ANN with a balanced training set, which is representatives of the actual data that the ANN will need to work with in real life. We will explore this in the next experiment.