Loss
A single number that measures how wrong a model's predictions are on the data it's shown. Training works by nudging the model to make this number as small as possible.
Think of It Like This
Think of it as a golf score — the lower it goes, the better the model is playing.
A loss function compares each prediction to the correct answer and boils the gap down to one number — cross-entropy for classification, mean squared error for regression. Training reads the gradient of that number to decide which way to adjust every weight, so a steadily falling loss is the clearest sign that learning is actually happening.