Skip to content

Playground / Unsupervised

Dimensionality reduction

Unroll a swiss roll with PCA, Kernel PCA, t-SNE and UMAP. Read the theory →

Puzzle: PCA meets a rolled-up sheet. Press Train, then find a method that unrolls it.

Data
More data options
Model A
Input · first 3 of 3 dimensions

Drag the 3-D view to rotate it.

PCA

Drag the 3-D view to rotate it.

loss per step (axis fitted to the range)

Train a model to see its loss curve.

Step -train ━test ┅

colour = position along the manifold

Press Train. The verdict appears here.