The Binary BrothersTwo Mentors, One Mission – Your Selection
All mock tests are FREE till 31 December — register to save your progress
Paper 2 CS · UNIT 10 · MOCK TEST

Artificial Intelligence (AI) — Mock Test 2

25 questions · about 30 minutes. Press End Mock any time to see your score and the correct answers.

0 / 25 answered 00:00
Q1. Match List I with List II
List IList II
(A) Natural language processing(I) A method of training an algorithm by rewarding desired behaviour and/or punishing undesired behaviour.
(B) Reinforcement learning(II) System designed to emulate the decision-making abilities of a human expert.
(C) Support vector machine(III) A branch of AI focused on understanding and generating human language.
(D) Expert system(IV) A machine learning technique that finds the hyperplane that best separates different classes in a feature space.

Directions (Q91–95): Artificial Neural Networks (ANNs) are computational models inspired by the human brain's neural networks. They consist of interconnected nodes, or neurons, organized into layers: an input layer, one or more hidden layers and an output layer. Each connection between neurons has a weight that adjusts as learning progresses, allowing the network to adapt and improve its performance. ANNs are particularly effective in recognizing patterns, making them valuable for tasks such as image and speech recognition, natural language processing and predictive analytics. Learning in ANNs typically involves training algorithms like back propagation, which minimize the error by adjusting the weights. As a subset of machine learning, ANNs have revolutionized the field of Artificial Intelligence by providing solutions to complex problems that traditional algorithms struggle with.

Q2. What is the role of the Back Propagation algorithm?

Directions (Q91–95): Artificial Neural Networks (ANNs) are computational models inspired by the human brain's neural networks. They consist of interconnected nodes, or neurons, organized into layers: an input layer, one or more hidden layers and an output layer. Each connection between neurons has a weight that adjusts as learning progresses, allowing the network to adapt and improve its performance. ANNs are particularly effective in recognizing patterns, making them valuable for tasks such as image and speech recognition, natural language processing and predictive analytics. Learning in ANNs typically involves training algorithms like back propagation, which minimize the error by adjusting the weights. As a subset of machine learning, ANNs have revolutionized the field of Artificial Intelligence by providing solutions to complex problems that traditional algorithms struggle with.

Q3. What is the role of weights in an ANN?

Directions (Q91–95): Artificial Neural Networks (ANNs) are computational models inspired by the human brain's neural networks. They consist of interconnected nodes, or neurons, organized into layers: an input layer, one or more hidden layers and an output layer. Each connection between neurons has a weight that adjusts as learning progresses, allowing the network to adapt and improve its performance. ANNs are particularly effective in recognizing patterns, making them valuable for tasks such as image and speech recognition, natural language processing and predictive analytics. Learning in ANNs typically involves training algorithms like back propagation, which minimize the error by adjusting the weights. As a subset of machine learning, ANNs have revolutionized the field of Artificial Intelligence by providing solutions to complex problems that traditional algorithms struggle with.

Q4. Which of the following is/are application area(s) of ANN?
(A) Natural Language Processing
(B) Image Processing
(C) Pattern Recognition
(D) Speech Recognition
Choose the correct answer from the options given below:

Directions (Q91–95): Artificial Neural Networks (ANNs) are computational models inspired by the human brain's neural networks. They consist of interconnected nodes, or neurons, organized into layers: an input layer, one or more hidden layers and an output layer. Each connection between neurons has a weight that adjusts as learning progresses, allowing the network to adapt and improve its performance. ANNs are particularly effective in recognizing patterns, making them valuable for tasks such as image and speech recognition, natural language processing and predictive analytics. Learning in ANNs typically involves training algorithms like back propagation, which minimize the error by adjusting the weights. As a subset of machine learning, ANNs have revolutionized the field of Artificial Intelligence by providing solutions to complex problems that traditional algorithms struggle with.

Q5. Artificial Neural Networks (ANNs) are inspired by:

Directions (Q91–95): Artificial Neural Networks (ANNs) are computational models inspired by the human brain's neural networks. They consist of interconnected nodes, or neurons, organized into layers: an input layer, one or more hidden layers and an output layer. Each connection between neurons has a weight that adjusts as learning progresses, allowing the network to adapt and improve its performance. ANNs are particularly effective in recognizing patterns, making them valuable for tasks such as image and speech recognition, natural language processing and predictive analytics. Learning in ANNs typically involves training algorithms like back propagation, which minimize the error by adjusting the weights. As a subset of machine learning, ANNs have revolutionized the field of Artificial Intelligence by providing solutions to complex problems that traditional algorithms struggle with.

Q6. Which of the following layers may be more than one in number?
Q7. What is the generic structure of a Multi-Agent System (MAS)?
Q8. A point x ∈ X of a fuzzy set A at which μA(x) = 0.5 is called a:
Q9. In a genetic algorithm optimization problem, the fitness function is f(x) = x² − 4x + 4. Given a population of four individuals with x values {1.5, 2.0, 3.0, 4.5}, what is the fitness value of the individual that will be selected as the parent for reproduction in one generation?
Q10. In a feed-forward neural network, the input layer has 4 neurons, the hidden layer 3 neurons and the output layer 2 neurons, all using the sigmoid activation. Inputs: [0.5, 0.8, 0.2, 0.6]. Input→hidden weights: W1 = [0.1, 0.3, 0.5, 0.2], W2 = [0.2, 0.4, 0.6, 0.2], W3 = [0.3, 0.5, 0.7, 0.2]. Hidden→output weights: W4 = [0.4, 0.1, 0.3], W5 = [0.5, 0.2, 0.4]. What is the output of the output layer (rounded to two decimals)?
Q11. Which of the following are commonly used parsing techniques in NLP for syntactic analysis?
(A) Top-down parsing
(B) Bottom-up parsing
(C) Dependency parsing
(D) Statistical machine translation
(E) Earley parsing
Choose the correct answer from the options given below:
Q12. In the context of alpha-beta pruning in game trees, which of the following statements are correct regarding cut-off procedures?
(A) Alpha-beta pruning can eliminate subtrees with certainty when the value of a node exceeds the alpha/beta bounds.
(B) The primary purpose of alpha-beta pruning is to save computation time by searching fewer nodes in the same tree.
(C) Alpha-beta pruning guarantees the optimal solution in all cases by exploring the entire game tree.
(D) Alpha and beta bounds are initialised to negative and positive infinity respectively at the root node.
Choose the correct answer from the options given below:
Q13. Match List I with List II
List IList II
(a) Greedy best-first search(I) Space complexity is linear in the depth d of the deepest optimal solution
(b) A*(II) Incomplete even if the search space is finite
(c) Recursive best-first search(III) Optimal if the optimal solution is reachable; otherwise returns the best reachable solution
(d) SMA*(IV) Computation and space complexity are too high
Q14. Match List I with List II (space complexity)
List IList II
(a) Hill climbing(I) O(bd)
(b) Best first search(II) O(bd)
(c) A* search(III) O(1)
(d) Depth first search(IV) O(bm)
Q15. Arrange the following encoding strategies used in Genetic Algorithms (GAs) in the correct sequence, starting from the initial step and ending with the final representation of solutions:
(a) Binary encoding
(b) Real-valued encoding
(c) Permutation encoding
(d) Gray coding
Choose the correct answer from the options given below:
Q16. Arrange the following steps in the correct sequence for applying K-means clustering to a data set:
(a) Randomly initialise cluster centroids
(b) Assign each data point to the nearest cluster centroid
(c) Update the cluster centroids based on the mean of the points assigned to each cluster
(d) Specify the number of clusters K
(e) Repeat steps (b) and (c) until convergence
Choose the correct answer from the options given below:
Q17. Statement I: The fuzzifier is a part of a fuzzy system.
Statement II: The inference engine is a part of a fuzzy system.
Q18. Which of the following is NOT a property of a good system for the representation of knowledge in a particular domain?
Q19. Which of the following is NOT a mutation operator in a genetic algorithm?
Q20. Which is NOT a component of the natural language understanding process?
Q21. Match List I with List II
List IList II
A. Expert systemI. Decision tree
B. Fuzzy systemII. Scramble
C. Operator in genetic algorithmIII. Inference engine
D. Supervised techniqueIV. Mycin
Q22. Given below are two statements: one is labelled as Assertion A and the other is labelled as Reason R.
Assertion A: Dendral is an expert system.
Reason R: The rationality of an agent is not related to its reaction to the environment.
Q23. Which of the following is NOT a solution representation in a genetic algorithm?
Q24. Consider the following statements:
A. C-fuzzy means clustering is a supervised method of learning.
B. PCA is used for dimension reduction.
C. Apriori is not a supervised technique.
D. When a machine-learning model becomes so specially tuned to its exact input data that it fails to generalise to other similar data, it is called underfitting.
Choose the correct answer from the options given below:
Q25. Which is NOT a basic approach to the problem of conflict resolution in a production system?