TIL If you take a dataset in 1,000 dimensions, and calculate the Euclidean distance between a point and its *nearest* neighbor, and then compare it to the distance to its *farthest* neighbor...
the difference approaches zero 😵
TIL If you take a dataset in 1,000 dimensions, and calculate the Euclidean distance between a point and its *nearest* neighbor, and then compare it to the distance to its *farthest* neighbor...
the difference approaches zero 😵