To get an idea on the performance of a prediction model a loss function is typically used. The loss function can quantify how good or bad a model is based on the prediction a model makes and the target output or 'ground truth', these inputs need to be of the same dimension. A loss function compares these two inputs and maps them to a non-negative real number using some kind of operation. Well known loss functions include the Counting loss and Mean Squared Error Loss (MSE)
| \( L \) | This is the symbol for a loss function. It is a function that calculates how wrong a model's inference is compared to where it should be. |
| \( n \) | This symbol represents any given whole number, \( n \in \htmlClass{sdt-0000000014}{\mathbb{W}}\). |
| \( \mathbb{R} \) | This is the symbol for the set of real numbers. |