
k-means clustering
Data Skeptic
Unsupervised Learning and Camean's Clustering
Camean's clustering is the poster child for unsupervised learning. The algorithm requires one perameter, which means if your a set has n elements, then there are k to the end, possible labellings you could output. There's no way we can check every possible combination of labellings to find the best one if that n gets too big. For this optimization problem, the best score is the one that minimizes the average distance between your data and the associated centroids.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.