Accelerating k-nearest Neighbors 600x Using RAPIDS cuML

Originally published at: Accelerating k-nearest Neighbors 600x Using RAPIDS cuML | NVIDIA Developer Blog

This post was originally published on the RAPIDS AI Blog. k-Nearest Neighbors classification is a straightforward machine learning technique that predicts an unknown observation by using the k most similar known observations in the training dataset. In the second row of the example pictured above, we find the seven digits 3, 3, 3, 3, 3,…