Unsupervised Learning & K-Means

What is the main goal of unsupervised learning?

• To classify labeled data

• To find hidden patterns in unlabeled data

• To predict future values

• To train a supervised model

Which of the following is an example of an unsupervised learning algorithm?

• Decision Trees

• Logistic Regression

• K-Means Clustering

• Support Vector Machines

What does the “K” in K-Means Clustering represent?

• The number of features in the dataset

• The number of clusters

• The number of iterations in training

• The distance metric used

How does K-Means initialize the cluster centroids?

• Randomly selecting K points from the dataset

• Placing them at the origin (0,0)

• Assigning all points to a single centroid

• Using supervised learning to determine initial positions

What distance metric is most commonly used in K-Means?

• Manhattan Distance

• Cosine Similarity

• Euclidean Distance

• Hamming Distance

Which of the following is a common method for choosing the optimal number of clusters (K) in K-Means?

• Backpropagation

• The Elbow Method

• Gradient Descent

• Confusion Matrix

What happens if K is chosen too large in K-Means?

• Some clusters may be empty

• The clusters will be too general

• The model may overfit and capture noise

• The algorithm will fail to converge

What happens when K-Means is applied to non-spherical clusters?

• It still works perfectly

• It may incorrectly cluster points due to its assumption of spherical shapes

• It automatically adjusts its distance metric

• It runs infinitely without stopping

Which of the following is NOT a stopping criterion for the K-Means algorithm?

• When centroids no longer change significantly

• When the maximum number of iterations is reached

• When the algorithm achieves 100% accuracy

• When the total within-cluster variance stops decreasing significantly