Skip to content
Learn AI by building
← World of AI

Machine Learning

Self-Supervised Learning

Learning useful representations from labels automatically created from the data.

Self-supervised learning creates training signals directly from the structure of unlabelled data. A model may predict masked words, missing image regions, future frames or whether two transformed examples came from the same source.

The model first learns general representations through pretraining and can later be adapted to specific tasks. This approach is central to modern language models, vision models and multimodal foundation models.

JOIN NOW

Begin the first module

It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.

Join any time · Build AI skills at your pace