AI engineering glossary · ML fundamentals
What is representation learning?
Representation learning (also called Feature learning): Methods where a model learns useful features from raw data automatically, rather than a person designing them by hand. The learned representations can then be reused for several tasks, which is the basis of modern deep learning and pretrained models.
Representation learning: an example
Instead of hand-crafting edge detectors, a model learns internal features from millions of raw images and reuses them for new tasks.
Related terms
More ML fundamentals terms
- Reproducibility
- Selection bias
- Self-supervised learning
- Semi-supervised learning
- Shortcut learning
- Spurious correlation
- Stratified k-fold
- Structural risk minimisation
Where you learn it
Representation 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.