Training your algorithm

Go to [[Week 2 - Introduction]] or back to the [[Main AI Page]]

This applies to [[Supervised Learning]]

First you show the learning algorithm data that represents what it's looking for, then what it's not looking for, over and over again while it modifies its internal values until it has learned to tell the difference between what it is looking for and what it is not.

You typically split your training data set into three sets.

• [[The training set]]
  • The data used to train the model
• [[The validation set]]
  • The data used to validate our results and fine-tune the parameters
• [[The testing set]]
  • The testing set is data the model has never seen before so we can check that our model works