SESKStuff Everyone Should Know
SESK: Stuff Everyone Should Know · sesk.info/ai-supervised-learning-labels

What makes machine learning "supervised"?

It learns from examples that come with the right answers (labels).

Start playing free

  1. A human watches the computer while it trains
  2. It trains on examples paired with correct labels ✔
  3. It learns only from examples without labels

Why: Supervised learning trains a model on features plus their matching labels, the known answers. It is like studying with a set of questions and their answer key.

Huh, didn't know that: Spam filters are a classic example: each training email comes labeled spam or not spam.

The dad joke
My model wanted unsupervised learning. I said not until it finishes its homework.
Like this card?
Play the game

References

Answer: It trains on examples paired with correct labels. Supervised learning trains a model on features plus their matching labels, the known answers. It is like studying with a set of questions and their answer key.

  1. Google Machine Learning Glossary: supervised machine learning developers.google.com/machine-learning/glossary
    Training a model from features and their corresponding labels.
    Checked 2026-10-10.

Think this answer is wrong? Tap "Challenge this answer" on the card in the game and tell us why.

Test yourself in the game

Artificial IntelligenceIn a model predicting house prices from size and bedrooms, what is the label?Artificial IntelligenceWhat does a membership inference attack try to learn?Artificial IntelligenceIs every use of copyrighted work for AI training automatically fair use?

That's stuff everyone should know.