Data in its raw form might not be ideal for training a network. There are some changes we can make to the data that are often desired or sometimes necessary in order to make training faster, simpler, or to ensure that it converges on a solution in the first place.

This video covers three reasons why it’s important for deep learning systems:

1) Preprocessing can transform the data into a form that is suitable for the network architecture

2) Preprocessing can help reduce the dimensions of your data and make patterns more obvious

3) Preprocessing can adjust the training data to ensure the entire solution space is covered.