Self-supervised learning vs Supervised learning

Why they differ

Both learn from right answers, but in supervised learning people write the answers; here they are cut out of the data itself.

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.

Supervised learning

Machine learning basics

Machine learning from examples that come with the right answer attached, such as emails already marked spam or not spam.

Formal

A form of machine learning in which each training example is paired with a label giving the wanted output, and the model learns to map new inputs to the right label.

In plain English

Like learning with an answer key. You try each exercise, check the key, and correct yourself.

In practice

A region's security team labels thousands of past alerts as real attacks or false alarms, and a model trained on them learns to sort new alerts the same way.

Why it matters

The model can only be as good as its labels; labels are often made by people paid per item, and their mistakes and biases become the model's.

Shared connections

Machine learning Training data Unsupervised learning