thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Foundational

Normalization

Min-max scaling that rescales a feature to a fixed range, usually 0 to 1.

Definition

Normalization computes (x - min) / (max - min). It preserves the shape of the distribution but is sensitive to outliers, which compress the remaining values. In other contexts, normalization can also mean scaling vectors to unit length, as done before cosine similarity.

Example

Scaling pixel values from 0-255 to 0-1 before training an image model.

Exam tip

Normalization bounds values; standardization centers them. Outliers favor standardization.

Related terms