Explain 'Manifold Learning'.

Explain 'Manifold Learning'.

Approach: Describe non-linear dimensionality reduction based on the idea that high-dimensional data lies on a lower-dimensional manifold.

A type of non-linear dimensionality reduction. It assumes that the observed high-dimensional data actually lies on a lower-dimensional manifold (a curved surface) embedded within the high-dimensional space.

Follow-up: Name a common algorithm (e.g., t-SNE or UMAP).

Key concepts: t-sne, isomap, topology.