Artificial Intelligence MCQs with Answers
Practice important Artificial Intelligence MCQs with answers and explanations.
Chapter: 37
Q1161:
Decision trees represent knowledge in the form of
A. Graphs
B. Rules
C. Tables
D. Trees
Correct Answer:
D
Chapter: 37
Q1162:
Minimal generalization is applied to S set when example is
A. Positive
B. Negative
C. Irrelevant
D. Test
Correct Answer:
A
Chapter: 37
Q1163:
Minimal specialization is applied to G set when example is
A. Positive
B. Negative
C. Irrelevant
D. Test
Correct Answer:
B
Chapter: 37
Q1164:
The purpose of Candidate-Elimination is to find
A. All possible consistent hypotheses
B. The most general hypothesis
C. The simplest hypothesis
D. The first matching example
Correct Answer:
A
Chapter: 37
Q1165:
The first hypothesis in S set is usually
A. Most specific
B. Most general
C. Random
D. None
Correct Answer:
A
Chapter: 37
Q1166:
In Candidate-Elimination, training examples are processed
A. Once
B. Multiple times
C. Only negative
D. Only positive
Correct Answer:
A
Chapter: 38
Q1167:
What does ID3 stand for?
A. Incremental Dichotomizer 3
B. Iterative Decision Design
C. Interactive Dichotomizer 3
D. Information Depth 3
Correct Answer:
C
Chapter: 38
Q1168:
Which step is performed first in the ID3 algorithm?
A. Build leaf nodes
B. Calculate entropy
C. Find the root node
D. Choose the attribute with least value
Correct Answer:
C
Chapter: 38
Q1169:
What is the primary function used in ID3 to evaluate attributes?
A. ENTROPY()
B. FIND()
C. GAIN()
D. INFO()
Correct Answer:
C
Chapter: 38
Q1170:
Which attribute becomes the root node in ID3?
A. Attribute with least entropy
B. Random attribute
C. Attribute with highest frequency
D. Attribute with maximum information gain
Correct Answer:
D
Chapter: 38
Q1171:
Entropy measures what in a dataset?
A. Speed of computation
B. Purity/impurity of examples
C. Size of dataset
D. Training time
Correct Answer:
B
Chapter: 38
Q1172:
What is the value of entropy when all examples belong to one class?
A. 1
B. 0.5
C. Undefined
Correct Answer:
D
Chapter: 38
Q1173:
In entropy calculation, what is the value of log2(1)?
A. 1
B. 2
D. -1
Correct Answer:
C
Chapter: 38
Q1174:
Which of the following represents a correct entropy formula?
A. Entropy(S) = p+ - p-
B. Entropy(S) = - p+log2 p+ - p-log2 p-
C. Entropy(S) = (p+ + p-)log2(p+ / p-)
D. Entropy(S) = p+ * p-
Correct Answer:
B
Chapter: 38
Q1175:
When does ID3 stop splitting further in decision tree construction?
A. When gain is zero
B. When max height is reached
C. When entropy is 1
D. When attributes are exhausted and leaf nodes are pure
Correct Answer:
D
Chapter: 38
Q1176:
What is the purpose of Information Gain in ID3?
A. Reduce size of tree
B. Reduce entropy
C. Count attributes
D. Sort attributes by name
Correct Answer:
B
Chapter: 38
Q1177:
Information Gain is calculated using which metric?
A. Speed of learning
B. Entropy reduction
C. Dataset size
D. Root path length
Correct Answer:
B
Chapter: 38
Q1178:
Which attribute was selected as the root in the given example?
A. A
B. B
C. E
D. C
Correct Answer:
A
Chapter: 38
Q1179:
What was the information gain of attribute A in the given example?
A. 0.02
B. 0.97
C. 0.57
D. 1
Correct Answer:
C
Chapter: 38
Q1180:
What was the entropy of the full training set S in the example?
A. 1
B. 0.57
C. 0.97
Correct Answer:
C