Skip to content

Glossary: Calculus for ML

Standardize

Also written: standardizing, standardization, scaling inputs, centering

Subtract the mean and divide by the standard deviation so inputs are on a similar scale centered on 0. This reshapes the loss into a rounder bowl that gradient descent crosses easily. New data must use the training mean and std.

Where the book teaches it

Related terms

Standard deviationLearning rateFeature