Machine Learning Fundamentals · Unsupervised learning

Dimensionality reduction (PCA)

Compressing many correlated features into fewer new ones that still capture most of the original variation.

Also known as: PCA, principal component analysis.

Start a lesson on Dimensionality reduction (PCA)

Learn first

• Feature engineering and scaling: Reshaping raw data (scaling numbers, encoding categories) into a form a model can actually learn from well.

Related topics

• K-means clustering: Grouping unlabeled points into k clusters by repeatedly assigning them to the nearest center and recomputing centers.