Mean Absolute Error

The average loss per example when L1 loss is used. Calculate Mean Absolute Error as follows: 1. Calculate the L1 loss for a batch. 2. Divide the L1 loss by the number of examples in the batch.

where: - $n$ is the number of examples. - $y$ is the actual value of the label. - $\hat{y}$ is the value that the model predicts for $y$. --- For example, consider the calculation of L1 loss on the following batch of five examples: Loss (difference between actual and predicted) | --- | 1 | 1 | 3 | 2 | 1 | | 8 = L1 loss | So, L1 loss is 8 and the number of examples is 5. Therefore, the Mean Absolute Error is:

Contrast Mean Absolute Error with Mean Squared Error and Root Mean Squared Error.

Practitioners refer to mean absolute error when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.