Skip to content

Saturday, October 10, 2026

Live
Loading the latest AI news…

Glossary · How models work

Supervised learning

Supervised learning trains a model on examples that come with the right answer attached — photos labelled "cat" or "dog", loans marked "repaid" or "defaulted". The model learns to predict the label for new examples.

In one line, for a 12-year-old

Supervised learning is studying with an answer key.

An example

A model learns to estimate house prices from thousands of past sales where the final price is known.

Why it matters to people

The answers in the key come from past human decisions. If past hiring or lending was unfair, a model can learn to repeat that unfairness.