MCQs / Computer Science / NSCT: AI, Machine Learning & Data Analytics

NSCT: AI, Machine Learning & Data Analytics MCQs — Computer Science (page 5)

127 multiple-choice questions on NSCT: AI, Machine Learning & Data Analytics from Computer Science, each with the correct answer and, where available, a teacher's explanation. Read through them to revise the chapter, then practise the same questions one by one to test yourself.

101. Actual values [100, 150, 200] and predictions [110, 140, 230]. What is the Mean Squared Error (MSE)?

  1. 19.15
  2. 366.67
  3. 16.67
  4. 1100

Answer: B) 366.67

Explanation: Mean of squared errors = 366.67. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

102. SVM tries to find a decision boundary with:

  1. Random splits
  2. The most layers
  3. The maximum margin between classes
  4. The smallest number of features

Answer: C) The maximum margin between classes

Explanation: Support vectors define the margin. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

103. Actual values [10, 12, 8] and predictions [11, 10, 8]. What is the Mean Absolute Error (MAE)?

  1. 1.29
  2. 1
  3. 0.33
  4. 1.67

Answer: B) 1

Explanation: Errors [-1, 2, 0]; mean of absolute values = 1. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

104. A classifier's confusion matrix is: TP = 30, FP = 5, FN = 15, TN = 50. What is its precision?

  1. 66.7%
  2. 85.7%
  3. 14.3%
  4. 80%

Answer: B) 85.7%

Explanation: Precision = TP ÷ (TP + FP) = 30 ÷ 35 = 85.7%. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

105. A classifier's confusion matrix is: TP = 80, FP = 20, FN = 10, TN = 90. What is its precision?

  1. 80%
  2. 20%
  3. 85%
  4. 88.9%

Answer: A) 80%

Explanation: Precision = TP ÷ (TP + FP) = 80 ÷ 100 = 80%. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

106. k-NN classifies a new point by:

  1. A majority vote of its k nearest neighbours
  2. Drawing the widest margin
  3. Building a tree
  4. Computing word frequencies

Answer: A) A majority vote of its k nearest neighbours

Explanation: It needs scaled features. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

107. A value of 64 comes from data with mean 60 and standard deviation 8. What is its z-score?

  1. -0.5
  2. 4
  3. 0.5
  4. 1

Answer: C) 0.5

Explanation: z = (x − mean) ÷ std = (64 − 60) ÷ 8 = 0.5. Lesson 8.2 · AI, Machine Learning & Data Analytics

Discuss this question

108. A classifier's confusion matrix is: TP = 30, FP = 5, FN = 15, TN = 50. What is its F1-score (to 2 decimal places)?

  1. 0.80
  2. 0.76
  3. 0.75
  4. 0.57

Answer: C) 0.75

Explanation: F1 = 2PR ÷ (P + R) = 2 × 0.86 × 0.67 ÷ (0.86 + 0.67) = 0.75. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

109. A dataset of 1000 samples is used in 5-fold cross-validation. How many samples are in each test fold?

  1. 166
  2. 200
  3. 800
  4. 5

Answer: B) 200

Explanation: 1000 ÷ 5 = 200; the other 800 are used for training in that round. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

110. A classifier's confusion matrix is: TP = 80, FP = 20, FN = 10, TN = 90. What is its accuracy?

  1. 85%
  2. 80%
  3. 88.9%
  4. 40%

Answer: A) 85%

Explanation: Accuracy = (TP + TN) ÷ total = 170 ÷ 200 = 85%. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

111. Deep learning is a subset of machine learning that uses:

  1. Neural networks with many layers
  2. Rule-based expert systems only
  3. SQL queries
  4. Only decision trees

Answer: A) Neural networks with many layers

Explanation: Deep = many hidden layers. Lesson 8.1 · AI, Machine Learning & Data Analytics

Discuss this question

112. Machine learning is best described as:

  1. Writing longer programs
  2. Systems that learn patterns from data instead of being explicitly programmed for every rule
  3. Building faster hardware
  4. Designing databases

Answer: B) Systems that learn patterns from data instead of being explicitly programmed for every rule

Explanation: ML improves with experience (data). Lesson 8.1 · AI, Machine Learning & Data Analytics

Discuss this question

113. An R² value of 1.0 for a regression model means:

  1. The model explains all the variance in the target
  2. The error is very high
  3. The model is useless
  4. The model is a classifier

Answer: A) The model explains all the variance in the target

Explanation: R² measures goodness of fit. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

114. Alpha-beta pruning is used to speed up:

  1. Linear regression
  2. Minimax search in two-player games
  3. k-means
  4. Sorting

Answer: B) Minimax search in two-player games

Explanation: It skips branches that cannot affect the decision. Lesson 8.1 · AI, Machine Learning & Data Analytics

Discuss this question

115. A classifier's confusion matrix is: TP = 45, FP = 5, FN = 5, TN = 45. What is its accuracy?

  1. 91%
  2. 10%
  3. 45%
  4. 90%

Answer: D) 90%

Explanation: Accuracy = (TP + TN) ÷ total = 90 ÷ 100 = 90%. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

116. Reusing a model pretrained on a large dataset and fine-tuning it on a small dataset is:

  1. Clustering
  2. Data leakage
  3. Reinforcement learning
  4. Transfer learning

Answer: D) Transfer learning

Explanation: It saves data and training time. Lesson 8.5 · AI, Machine Learning & Data Analytics

Discuss this question

117. A chess-playing program that cannot do anything else is an example of:

  1. Narrow AI
  2. General AI
  3. Super AI
  4. Human intelligence

Answer: A) Narrow AI

Explanation: It excels at one specific task. Lesson 8.1 · AI, Machine Learning & Data Analytics

Discuss this question

118. A classifier's confusion matrix is: TP = 8, FP = 2, FN = 12, TN = 978. What is its accuracy?

  1. 80%
  2. 0.8%
  3. 98.6%
  4. 40%

Answer: C) 98.6%

Explanation: Accuracy = (TP + TN) ÷ total = 986 ÷ 1000 = 98.6%. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

119. A classifier's confusion matrix is: TP = 80, FP = 20, FN = 10, TN = 90. What is its recall?

  1. 11.1%
  2. 80%
  3. 88.9%
  4. 85%

Answer: C) 88.9%

Explanation: Recall = TP ÷ (TP + FN) = 80 ÷ 90 = 88.9%. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

120. A classifier's confusion matrix is: TP = 45, FP = 5, FN = 5, TN = 45. What is its recall?

  1. 90%
  2. 89%
  3. 10%
  4. 91%

Answer: A) 90%

Explanation: Recall = TP ÷ (TP + FN) = 45 ÷ 50 = 90%. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

121. A classifier's confusion matrix is: TP = 25, FP = 25, FN = 25, TN = 25. What is its accuracy?

  1. 51%
  2. 25%
  3. 49%
  4. 50%

Answer: D) 50%

Explanation: Accuracy = (TP + TN) ÷ total = 50 ÷ 100 = 50%. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

122. A neural network layer between the input and output layers is a:

  1. Pooling layer only
  2. Output layer
  3. Hidden layer
  4. Embedding table

Answer: C) Hidden layer

Explanation: Deep networks have many hidden layers. Lesson 8.5 · AI, Machine Learning & Data Analytics

Discuss this question

123. Naive Bayes assumes that features are:

  1. Unlabelled
  2. Conditionally independent given the class
  3. Normally distributed images
  4. Always correlated

Answer: B) Conditionally independent given the class

Explanation: The "naive" assumption simplifies probability calculations. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

124. A classifier's confusion matrix is: TP = 40, FP = 10, FN = 5, TN = 45. What is its recall?

  1. 85%
  2. 80%
  3. 11.1%
  4. 88.9%

Answer: D) 88.9%

Explanation: Recall = TP ÷ (TP + FN) = 40 ÷ 45 = 88.9%. Lesson 8.3 · AI, Machine Learning & Data Analytics

Discuss this question

125. A feature ranges from 5 to 25. What is the min-max normalized value of 5?

  1. 0
  2. 0.25
  3. 0.2
  4. 1

Answer: A) 0

Explanation: (x − min) ÷ (max − min) = (5 − 5) ÷ (25 − 5) = 0. Lesson 8.2 · AI, Machine Learning & Data Analytics

Discuss this question

Previous Page 5 of 6 Next

Practise NSCT: AI, Machine Learning & Data Analytics MCQs

More Computer Science chapters