AI engineering glossary · ML fundamentals
What is self-supervised learning?
Self-supervised learning: Learning in which the training signal is created from the data itself rather than from human labels. A model hides or corrupts part of the input and learns to predict it, such as the next word in a sentence. It lets models learn from huge unlabelled collections and underpins modern language and vision systems.
Self-supervised learning: an example
A language model is shown 'The monsoon arrives in ___' and learns to predict the missing word, using only raw text with no human annotation.
Related terms
More ML fundamentals terms
- Semi-supervised learning
- Shortcut learning
- Spurious correlation
- Stratified k-fold
- Structural risk minimisation
- Supervised learning
- Target leakage
- Temporal leakage
Where you learn it
Self-supervised learning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.