Home About

Category

Notes Reference

Tags

GameDesign (13) LinearAlgebra (11) AutomatedTesting (6) SoftwareEngineering (5) Roblox (5) Zettelkasten (5) MachineLearning (4) More

Notes by Lex

Mean Absolute Difference - L1 Loss

Feb 03, 2016 permanent    MachineLearning  LossFunctions

Mean Absolute Difference (MAE) is a function for assessing Regression predictions. It's also as L1 Loss because it takes the L1 Norm of the error vector.

Steps

  1. Calculate error vector as labels - predictions
  2. Take the absolute values of the errors
  3. Take the mean of all values.

An alternative to Root mean-squared error - L2 Loss.

References

  • What Are L1 and L2 Loss Functions