Loss Function
The formula that scores how wrong a model's prediction is — the thing training tries to minimise.
A loss function turns the gap between prediction and truth into a single number. Training is nothing more than searching for parameters that make that number small. Choosing the loss is choosing what the model will care about, which makes it a quietly consequential decision.
In practice: Predicted 0.9 where the answer was 1.0 — loss is small, so the correction is small.