training
Teaching a model by showing it many examples and correcting its mistakes.
Training is how a model learns. It is shown an example, makes a guess, and is told how wrong the guess was. Its internal numbers are then adjusted slightly to do better next time. Repeating this millions of times gives a model that works. Training is slow and expensive, and usually happens once, before anyone uses the model.
Think of it as
Like learning to throw darts. Each throw shows how far you missed, and you adjust a little. After thousands of throws, you hit the board without thinking.
Example
A bank trains a fraud model on years of past card payments, each labelled fraud or genuine. Training takes days on powerful computers. After that, the finished model checks each new payment in a fraction of a second.