AI engineering glossary · ML fundamentals
What is semi-supervised learning?
Semi-supervised learning: Learning that combines a small amount of labelled data with a large amount of unlabelled data. The unlabelled examples reveal the shape of the input distribution, which helps the model draw better boundaries than the few labels could alone. It is attractive when labelling requires expensive expert time.
Semi-supervised learning: an example
A hospital has 500 X-rays labelled by radiologists and 50,000 unlabelled ones; a model uses both, for example by assigning confident guesses to the unlabelled images and retraining.
Related terms
More ML fundamentals terms
- Shortcut learning
- Spurious correlation
- Stratified k-fold
- Structural risk minimisation
- Supervised learning
- Target leakage
- Temporal leakage
- Test set
Where you learn it
Semi-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.