Back to Subject

Unit 1: Introduction to Unsupervised Learning & K-Means - Practice Quiz

INT423 — Machine Learning-Ii 50 Questions
0 Correct 0 Wrong 50 Left
0/50

1 What is the primary characteristic of Unsupervised Learning?

A. The algorithm trains on data without labels
B. The algorithm predicts a continuous numerical value
C. The algorithm uses a feedback loop for rewards
D. The algorithm trains on labeled data

2 Which of the following is a primary goal of clustering?

A. To classify images into predefined categories
B. To reduce the noise in a signal
C. To predict future values based on past trends
D. To group similar data points together

3 In the context of K-Means, what does 'K' represent?

A. The dimension of the features
B. The number of clusters
C. The number of data points
D. The number of iterations

4 What kind of problem is K-Means designed to solve?

A. Reinforcement Learning
B. Classification
C. Regression
D. Clustering

5 What is a 'centroid' in the K-Means algorithm?

A. The geometric center of a cluster
B. An outlier in the dataset
C. The data point furthest from the center
D. The boundary line between clusters

6 Which distance metric is most commonly used in standard K-Means?

A. Manhattan distance
B. Hamming distance
C. Euclidean distance
D. Cosine similarity

7 What is the first step of the K-Means algorithm?

A. Update the centroids
B. Assign points to the nearest cluster
C. Initialize cluster centroids
D. Calculate the total error

8 During the assignment step of K-Means, how is a data point assigned to a cluster?

A. To the cluster with the highest variance
B. Randomly
C. To the cluster with the most points
D. To the cluster with the closest centroid

9 What happens during the update step of the K-Means algorithm?

A. Centroids are moved to the mean of their assigned points
B. Points are reassigned to different clusters
C. The number of clusters (K) is increased
D. New data points are added

10 When does the K-Means algorithm stop iterating?

A. After exactly 10 iterations
B. When K is equal to N
C. When the centroids do not change significantly
D. When the training error is zero

11 What is the optimization objective (cost function) of K-Means?

A. Maximize Inter-cluster distance
B. Maximize the Silhouette score
C. Minimize Within-Cluster Sum of Squares (WCSS)
D. Minimize the number of clusters

12 The objective function of K-Means is non-convex. What does this imply?

A. It requires labeled data
B. It always finds the global minimum
C. It may get stuck in a local minimum
D. It cannot be optimized

13 Which of the following is a disadvantage of the K-Means algorithm?

A. It cannot handle numerical data
B. It is computationally very expensive for small datasets
C. It works only on labeled data
D. It is sensitive to outliers

14 If you set K equal to the number of data points (N), what will the WCSS be?

A. Infinity
B. Maximum possible value
C. Zero
D. Undefined

15 What is the 'Elbow Method' used for?

A. Handling outliers
B. Speeding up convergence
C. Determining the optimal number of clusters (K)
D. Initializing centroids

16 In the Elbow Method plot, what is typically on the Y-axis?

A. Time taken
B. Number of clusters (K)
C. Accuracy
D. Inertia or WCSS

17 What is the 'Random Initialization Trap' in K-Means?

A. Random data points cannot be clustered
B. Choosing K randomly leads to errors
C. The algorithm fails if data is random
D. Randomly picking centroids can lead to poor local optima

18 What is K-Means++?

A. A method to choose the optimal K
B. A smarter initialization technique for K-Means
C. A post-processing step for K-Means
D. A version of K-Means for supervised learning

19 How does K-Means++ select the first centroid?

A. It picks one data point uniformly at random
B. It calculates the global mean
C. It picks the point with the highest variance
D. It chooses the point furthest from the origin

20 What is the difference between Hard Clustering and Soft Clustering?

A. Hard clustering allows overlapping; Soft does not
B. Hard clustering assigns a point to one cluster; Soft assigns probabilities
C. Hard clustering is faster; Soft is slower
D. Hard clustering uses K-Means; Soft uses Decision Trees

21 Standard K-Means is an example of which type of clustering?

A. Soft Clustering
B. Density-based Clustering
C. Hard Clustering
D. Hierarchical Clustering

22 Which algorithm is a well-known example of Soft Clustering?

A. K-Means
B. Fuzzy C-Means
C. Agglomerative Clustering
D. DBSCAN

23 If a data point has a membership vector [0.7, 0.2, 0.1] for 3 clusters, this is an example of:

A. Regression
B. Hard Clustering
C. Outlier Detection
D. Soft Clustering

24 What shape of clusters does K-Means typically assume?

A. Spirals
B. Spherical or convex
C. Elongated shapes
D. Arbitrary shapes

25 Why is feature scaling (standardization/normalization) important in K-Means?

A. To prevent features with larger ranges from dominating the distance metric
B. It is not important
C. To convert categorical data to numerical
D. To ensure the algorithm runs faster only

26 What is the computational complexity of one iteration of K-Means?

A. O(e^N)
B. O(K N d)
C. O(N^2)
D. O(N * log N)

27 In the Elbow method, the 'elbow' point represents:

A. The point where K equals 1
B. The point where adding another cluster does not significantly reduce WCSS
C. The point where WCSS becomes zero
D. The point of maximum error

28 Which of the following implies that K-Means has converged?

A. The number of clusters decreases
B. The data becomes labeled
C. The assignment of points to clusters remains unchanged
D. WCSS increases

29 What is 'Inertia' in the context of Scikit-Learn's K-Means implementation?

A. The time taken to run
B. The sum of squared distances of samples to their closest cluster center
C. The number of iterations
D. The distance between cluster centers

30 Which strategy is used to mitigate the local optima problem in K-Means?

A. Use Manhattan distance
B. Decrease the learning rate
C. Run the algorithm multiple times with different initializations
D. Increase the number of clusters

31 Can K-Means handle categorical data directly?

A. Only if the data is ordinal
B. Yes, it works natively
C. No, it requires numerical data
D. Yes, using Hamming distance

32 In K-Means++, how is the probability of selecting the next centroid determined?

A. Proportional to the squared distance from the nearest existing centroid
B. Based on the density of the points
C. Randomly with uniform distribution
D. Inversely proportional to the distance from existing centroids

33 What is a 'Voronoi Diagram' in relation to K-Means?

A. A method to initialize K
B. A visualization where regions are defined by the closest centroid
C. A plot of the cost function
D. A type of soft clustering

34 If the clusters in the data are of very different densities and sizes, K-Means will:

A. Automatically adjust the metric
B. Likely fail to identify the correct clusters
C. Merge the clusters
D. Perform perfectly

35 Which step ensures K-Means is an unsupervised algorithm?

A. Iterating until convergence
B. Calculating the mean
C. Not using target labels for training
D. Minimizing WCSS

36 In the equation for WCSS, what is being squared?

A. The number of clusters
B. The distance between two centroids
C. The distance between a point and its assigned centroid
D. The number of iterations

37 Why is it often difficult to pick the optimal K using the Elbow method?

A. The plot is always a straight line
B. The 'elbow' might not be sharp or clear
C. It requires labeled data
D. It takes too long to compute

38 What is the primary role of the 'Coordinate Descent' concept in K-Means?

A. It calculates the distance
B. It is the method used to optimize the objective function
C. It is used to visualize data
D. It is used for initialization

39 If you perform K-Means on a dataset with 2 distinct well-separated blobs but set K=4, what happens?

A. It finds 2 clusters and ignores the other 2
B. It splits the natural blobs into smaller clusters
C. It merges the blobs
D. The algorithm crashes

40 In Soft Clustering, the sum of membership weights for a single data point across all clusters usually equals:

A. 0
B. 100
C. K
D. 1

41 Which of the following is NOT an application of K-Means?

A. Spam Classification (Supervised)
B. Document Clustering
C. Customer Segmentation
D. Image Compression (Color Quantization)

42 Does K-Means guarantee finding the global optimum for the WCSS?

A. Only if using Manhattan distance
B. No, it depends on initialization
C. Yes, always
D. Yes, if K is small

43 The computational cost of the distance calculation step for one point against K centroids is proportional to:

A. 1
B. N
C. K
D. N^2

44 Which component constitutes the 'model' after training K-Means?

A. The original dataset
B. The list of outliers
C. The coordinates of the final centroids
D. The Elbow plot

45 What is the relationship between Within-Cluster variance and Between-Cluster variance in a good clustering?

A. High within-cluster, Low between-cluster
B. Low within-cluster, High between-cluster
C. High within-cluster, High between-cluster
D. Low within-cluster, Low between-cluster

46 Lloyd's Algorithm is another name for:

A. KNN
B. K-Means Algorithm
C. Hierarchical Clustering
D. DBSCAN

47 In the context of image segmentation, what does a pixel represent in K-Means?

A. A cluster
B. A centroid
C. A label
D. A data point

48 Why might one choose a K value slightly different from the Elbow point?

A. Because the Elbow method is always wrong
B. To increase computational cost
C. To maximize WCSS
D. Based on business requirements or downstream tasks

49 If K=1, the centroid location will be:

A. A random data point
B. Undefined
C. The mean of the entire dataset
D. The origin (0,0)

50 What happens if a cluster becomes empty during K-Means iterations?

A. The algorithm stops
B. It is ignored and WCSS becomes 0
C. The K value increases
D. The empty cluster is usually re-initialized or removed
Next MCQ
Unit 2