Machine Learning Fundamentals · Feature engineering

Feature engineering and scaling

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

Also known as: normalization, standardization, one-hot encoding.

Start a lesson on Feature engineering and scaling

Learn first

• Types of ML problems: The basic split between supervised (labeled examples), unsupervised (no labels), and reinforcement learning.

Leads to

• Dimensionality reduction (PCA): Compressing many correlated features into fewer new ones that still capture most of the original variation.

Related topics

• Dimensionality reduction (PCA): Compressing many correlated features into fewer new ones that still capture most of the original variation.