K-Means Clustering

The simplest unsupervised algorithm: assign points to the nearest centroid and update centroids until convergence. Deceptively powerful in practice.

Learning Objectives

• →Implement the E-step (assignment) of k-means
• →Implement the M-step (centroid update)
• →Understand convergence and initialization sensitivity
• →Choose k with the elbow method

Coding Problems (2)