AI engineering glossary · ML fundamentals
What is PAC learning?
PAC learning (also called Probably approximately correct): A formal framework asking when an algorithm can, with high probability, find a model that is approximately correct after seeing a reasonable number of examples. It ties the needed sample size to accuracy demands and model class complexity, giving a mathematical basis for why learning from data can work at all.
PAC learning: an example
PAC results say roughly how many training examples suffice so that, with 95% confidence, a learned rule has error under 5%.
Related terms
- VC dimension
- Sample complexity
- Generalisation
- Hypothesis space
More ML fundamentals terms
- Parameter
- Parametric model
- Pipeline
- Probabilistic model
- Problem framing
- Random search
- Random seed
- Regression
Where you learn it
PAC 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.