K-Means Clustering Quiz

Answers and explanations appear as you take the quiz.

1. What does the 'K' in K-Means refer to?
   • The number of clusters you choose in advance
   • The number of data points
   • The number of training iterations
   • The number of features in the dataset
2. What are the two repeating steps in the K-Means loop?
   • Split clusters, then merge clusters
   • Assign points to nearest centroid, then move centroids to the mean
   • Label data, then train a classifier
   • Sort data, then remove outliers
3. What quantity does K-Means try to minimize?
   • The number of clusters
   • The distance between centroids
   • Within-cluster squared distance (inertia)
   • The number of features
4. Why is K-Means called an 'unsupervised' algorithm?
   • It uses predefined class labels to learn a boundary
   • It requires one label per initial centroid
   • It estimates labels only after supervised training
   • It groups inputs without target class labels
5. What is the 'elbow method' commonly used for?
   • Speeding up training
   • Choosing a good value of K
   • Initializing centroids
   • Removing duplicate points
6. Why can K-Means give different results on different runs?
   • K automatically changes on every run
   • Euclidean distance uses a random definition
   • Results depend on initial centroid positions
   • Convergence always produces the same global optimum
7. A K-Means cluster contains the one-dimensional values 2, 4, and 9. Where does its centroid move in the update step?
   • 5, the mean of the assigned values
   • 4, the middle observed value
   • 9, the largest assigned value
   • 15, the sum of the assigned values
8. A dataset contains two long, curved groups. Which K-Means limitation should the analyst consider?
   • The groups must have labels before clustering
   • K-Means always discovers curved boundaries exactly
   • Changing K guarantees the intended grouping
   • Euclidean distance to centroids can poorly represent elongated or non-spherical groups