Self-supervised learning vs Unsupervised learning

Why they differ

Neither needs human labels, but unsupervised learning only looks for groups and patterns, while self-supervised learning sets itself fill-in-the-gap tasks with a right answer.

Self-supervised learning

Machine learning basics

Machine learning where the right answers come from the data itself, for instance hiding a word in a sentence and guessing it back.

Formal

A form of machine learning that makes its own labels from unlabelled training data, by hiding or holding back part of each example and learning to fill it in from the rest.

In plain English

Like learning a song by pausing the recording mid-line, singing the next words yourself, then playing on to check. The song is its own answer key.

In practice

A region's speech-to-text team lets a model learn from thousands of hours of Danish speech by hiding short bits of sound and guessing them, then needs only a few hours of typed-up dictations to handle doctors' notes.

Why it matters

Removing the need for human labels is what made training on the whole web possible, and it is why whatever is on the web, good or bad, ends up in the model.

Unsupervised learning

Machine learning basics

Machine learning from examples with no answers attached, where the model finds groups, patterns or odd cases on its own.

Formal

A form of machine learning that works on training data without labels, finding structure in it, for example grouping similar items or flagging items that differ from the rest.

In plain English

Like sorting a box of mixed buttons into piles by colour and size without anyone telling you what the piles should be.

In practice

A monitoring tool at a hospital learns what normal logins look like and raises an alert when a nurse's account suddenly logs in at 3 a.m. from another country.

Why it matters

It can spot new, unknown threats nobody has labelled yet, but it also flags harmless unusual behaviour, so people must still judge the alerts.

Shared connections

Machine learning Supervised learning Training data