An algorithm that groups data into k clusters by distance.
k-Means is like dropping k pizza boxes at a party. Everyone stands by the closest box. Then each box moves to the middle of its hungry crowd.
You meet it in customer groups and image compression. Pick k badly, and the groups look weird.
Clustering
k-Means is a classic way to group data automatically.
Unsupervised Learning
It needs no human labels and groups by similarity.
GMM
GMM gives class probabilities, but k-Means gives one hard group.
EM
It repeats assign then update until the centers stop moving.