Unsupervised Learning

Finding structure in data that has no labels — clusters, groupings, or a compressed representation.

Machine Learning Beginner 1 min read

Definition

Unsupervised learning works on unlabelled data, looking for structure that is already there: clustering customers by behaviour, reducing dimensions for visualisation, or learning a compressed representation.

Because there is no ground truth, evaluation is genuinely hard — you are usually judging whether the structure found is useful rather than whether it is correct.

Self-supervised learning, which generates its own labels from the data (predict the next token, fill in the masked word), is what actually trains modern language models, and sits somewhere between the two.

How it relates to other terms

Contrast with Supervised Learning Training on examples that come with the right answer attached, so the model learns to map inputs to known labe... See also Embedding A list of numbers representing a piece of data, arranged so that similar things end up close together.
Referenced by
Supervised Learning Contrast with

Related terms

Neural Network

A model built from layers of simple weighted units, trained by adjusting those weights until the output matches the target.

Beginner Machine Learning

Overfitting

When a model learns the training data so closely — including its noise — that it performs worse on anything new.

Beginner Machine Learning

Embedding

A list of numbers representing a piece of data, arranged so that similar things end up close together.

Intermediate Machine Learning

Was this definition helpful?

Definitions are reviewed by our editorial team. Spotted a problem? Tell us.

Keep reading

Browse the glossary Suggest a correction