What is Data Normalization and why do we need it?

What is Data Normalization and why do we need it?

Approach: Explain scaling features to a uniform range.

The process of rescaling features to a specific range (usually [0,1] or standard normal). It is necessary because features with larger scales can dominate the loss function and gradients, slowing down optimization or making distance-based models inaccurate.

Follow-up: Is it necessary for Decision Trees?

Key concepts: feature scaling, convergence, standardization.