Knowledge Graph — Coursera Notes › Academic disciplines › Computer Science / Information Technology › Artificial Intelligence › Machine Learning & Data › Unsupervised Learning

Dimensionality Reduction

concept · part of Unsupervised Learning

A technique that simplifies data while preserving patterns, including methods like PCA, t-SNE, and autoencoders.

Inside Dimensionality Reduction (4)

• Autoencoders — Neural networks for nonlinear dimensionality reduction that learn to compress and reconstruct data, minimizing reconstruction error.
• LDA — Supervised linear dimensionality reduction that maximizes class separability by projecting data onto directions that best separate classes.
• PCA — A linear dimensionality reduction technique that projects data onto orthogonal principal components capturing maximum variance.
• t-SNE — A nonlinear dimensionality reduction technique that preserves local structure for visualization, ideal for revealing clusters.

This is the text view of an interactive 3D knowledge graph — open this page with JavaScript enabled to explore it visually.