Artificial Intelligence MCQs with Answers
Practice important Artificial Intelligence MCQs with answers and explanations.
Chapter: 39
Q1221:
Which of the following is a function of the activation function in a perceptron?
A. To compute weighted sum
B. To apply threshold
C. To produce output based on activation level
D. To add bias
Correct Answer:
C
Chapter: 39
Q1222:
The perceptron firing rule outputs 0 if the weighted sum plus bias ________.
A. Is greater than threshold
B. Is less than threshold
C. Equals threshold
D. Is greater than zero
Correct Answer:
B
Chapter: 39
Q1223:
An example of a linearly separable logical gate is ________.
A. XOR
B. AND
C. NOT
D. NAND
Correct Answer:
B
Chapter: 40
Q1224:
What do multiple layers of perceptrons introduce to solve problems like XOR?
A. One decision line
B. Multiple decision lines
C. No decision lines
D. Random decision lines
Correct Answer:
B
Chapter: 40
Q1225:
Each neuron in the hidden layer of a multilayer perceptron is responsible for what?
A. A different output
B. A different input
C. A different decision line
D. A different weight
Correct Answer:
C
Chapter: 40
Q1226:
Multiple layer perceptrons can construct which type of decision boundaries?
A. Linear
B. Non-linear
C. Circular
D. Square
Correct Answer:
B
Chapter: 40
Q1227:
Artificial Neural Networks resemble the brain because knowledge is acquired through ______.
A. A fixed program
B. A training process
C. Random guessing
D. Manual coding
Correct Answer:
B
Chapter: 40
Q1228:
What stores the knowledge in artificial neural networks?
A. Synaptic weights
B. Memory registers
C. Hardcoded rules
D. Database
Correct Answer:
A
Chapter: 40
Q1229:
Knowledge in artificial neural networks is ______ and distributed.
A. Explicit
B. Implicit
C. Random
D. Fixed
Correct Answer:
B
Chapter: 40
Q1230:
Which is NOT an advantage of Artificial Neural Networks?
A. Excellent for pattern recognition
B. Handles noisy data well
C. Requires no data
D. Good for generalization
Correct Answer:
C
Chapter: 40
Q1231:
A drawback of Artificial Neural Networks is that most machines are based on which architecture?
A. Von Neumann
B. Parallel Architecture
C. Distributed
D. Neural Architecture
Correct Answer:
A
Chapter: 40
Q1232:
Neural networks lack defined rules for building networks due to ______.
A. Too few variables
B. Too many variables
C. No variables
D. Fixed variables
Correct Answer:
B
Chapter: 40
Q1233:
Single layer networks consist of how many layers?
A. One input and one output
B. One input only
C. One output only
D. One hidden only
Correct Answer:
A
Chapter: 40
Q1234:
Multilayer networks contain which layers?
A. Input, hidden, output
B. Input, output only
C. Hidden, output only
D. Input only
Correct Answer:
A
Chapter: 40
Q1235:
Feed-forward networks have information flow in which direction?
A. Both directions
B. One direction forward
C. One direction backward
D. Random direction
Correct Answer:
B
Chapter: 40
Q1236:
Recurrent networks are also called ______ networks.
A. Feed-forward
B. Feedback
C. Partially connected
D. Fully connected
Correct Answer:
B
Chapter: 40
Q1237:
Which connectivity type means every neuron is connected to every neuron in the next layer?
A. Fully connected
B. Partially connected
C. Feed-forward
D. Recurrent
Correct Answer:
A
Chapter: 40
Q1238:
In neural networks, the knowledge is stored in the form of ______.
A. Explicit rules
B. Synaptic weights
C. Stored data files
D. Decision trees
Correct Answer:
B
Chapter: 40
Q1239:
The main benefit of multilayer perceptrons over single layer perceptrons is?
A. Simpler computation
B. Ability to classify non-linear problems
C. Less memory usage
D. Faster training
Correct Answer:
B
Chapter: 40
Q1240:
The hidden layer in a neural network helps to form ______.
A. Linear decision boundaries
B. Non-linear decision boundaries
C. No decision boundaries
D. Random output
Correct Answer:
B