Latent

Distances in many dimensions

Watch the distances between random points bunch together as the number of dimensions grows, the curse of dimensionality in one slider.

IntermediateExplained in Seeing high dimensions

Distances in many dimensions

160 random points in a cube. The chart shows every pairwise distance, divided by the average distance.

2
Farthest ÷ nearest neighbor40.8×
Spread of distances±48% of average

Try this

  • Compare 2, 10, 100, and 1,000 dimensions. Where does the farthest-to-nearest ratio drop below 2?

Try "embedding", "softmax", "overfitting", or "backpropagation".