AI engineering glossary · Classical ML algorithms
What is PCA (principal component analysis)?
Principal component analysis (also called PCA): A technique that finds new axes, ordered by how much of the data's variation they capture, by eigen-decomposition of the covariance matrix. Keeping only the first few axes compresses data with little information loss, aiding visualisation, noise removal and speed.
Principal component analysis: an example
Reducing 50 correlated survey answers to 5 components that keep 90% of the variance.
Related terms
More Classical ML algorithms terms
- Quadratic discriminant analysis
- Random forest
- RBF kernel
- Regression tree
- Residual
- Ridge regression
- Scree plot
- Shrinkage
Where you learn it
Principal component analysis is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.