Loss Functions - FL03/concision GitHub Wiki

Standard

Mean Absolute Error (MAE)

The mean squared error (MSE) is the average of the absolute of the differences between the predicted ($\hat{y_{i}}$) and actual values ($y_{i}$):

Definition

$$ Err = \frac{1}{n} \sum_{i=1}^{n} |y_i - \hat{y_{i}}| $$

Mean Squared Error (MAE)

The mean squared error (MSE) is the average of the squared differences between the predicted ($\hat{y_{i}}$) and actual values ($y_{i}$):

Definition

$$ Err = \frac{1}{n} \sum_{i=1}^{n} (y_i - \hat{y_{i}})^2 $$