Glossary term
Glossary term
Foundations
During the training of a supervised model, a measure of how far a model's prediction is from its label.
A loss function calculates the loss.
See Linear regression: Loss in Machine Learning Crash Course for more information.
Created for this library
An ML team tracks training and validation loss curves to compare candidate models on the same training schedule.
A research team experiments with several loss functions to find the one that aligns best with the business metric it cares about.
An ML platform team requires final-loss reporting in every release review so reviewers see how the new model compares to its predecessor.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License