What is a Mean Absolute Error?
The average loss per example when L1 loss is used.
Mean Absolute Error explained in plain English
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.
Example
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.
People also read
- A/B testing
A statistical way of comparing two (or more) techniques—the A and the B.
- ablation
A technique for evaluating the importance of a feature or component by temporarily removing it from a model.
- accuracy
The number of correct classification predictions divided by the total number of predictions.
- activation function
A function that enables neural networks to learn nonlinear (complex) relationships between features and the label.
- active learning
A training approach in which the algorithm chooses some of the data it learns from.
- adaptation
Synonym for tuning or fine-tuning.
- agglomerative clustering
See hierarchical clustering.
- anomaly detection
The process of identifying outliers.
- area under the PR curve
See PR AUC (Area under the PR Curve).
- area under the ROC curve
See AUC (Area under the ROC curve).