Beginner · 03

Three ways to learn

Learning with answers, learning without answers, and learning by trial and error.

5 min read · Tap underlined words for a definition

Not every problem comes with an answer key. Depending on what data you have, comes in three main flavours.

Supervised🐱🐶learns from labelsUnsupervisedfinds hidden groupsReinforcement🤖🌍⭐ +1actlearns from rewards
Supervised learning has labels, unsupervised finds structure on its own, reinforcement learns from rewards.

Supervised learning

Every example comes with the right answer, called a label. Photo → "cat". House details → price.

Predicting a category is classification. Predicting a number is regression.

Most practical ML today is supervised.

Unsupervised learning

No labels at all. The model looks for structure by itself.

Example: grouping customers into types by shopping habits (clustering), without anyone saying what the types are.

Reinforcement learning

An agent takes actions in an environment and gets rewards or penalties.

No one tells it the right move; it learns which actions pay off over time. This is how AlphaGo learned to beat world champions at Go.

Quick check

You have 50,000 photos of skin spots, each labelled by a doctor as harmless or worrying. Which kind of learning fits?

Self-supervised: the secret behind chatbots

A clever trick: make labels out of the data itself. Hide the next word of a sentence and ask the model to guess it.

The internet becomes one giant answer key. This is how large language models are pre-trained.

Quick check

A robot learns to walk by trying moves and getting points for staying upright. That's…

Before you drift off

  • Supervised: learn from labelled examples (classification or regression).
  • Unsupervised: find hidden structure without labels.
  • Reinforcement: learn actions from rewards.
  • Self-supervised: make labels from the data itself, which is how LLMs pre-train.

Terms in this lesson

Go deeper, free and open

That's the lesson

Three ways to learn · 5 min

Each lesson you finish lights a star.

Finish & continue · Up nextNeural networks, gentlyBeginner · 6 min

Spotted a mistake? Suggest an edit

Previous: How machines learn