25 questions · about 30 minutes. Press End Mock any time to see your score and the correct answers.
Fuzzy logic is a form of ____
Correct answer: D. Many valued logic 4 Ws
Fuzzy logic allows truth values anywhere in [0, 1], so it is a many-valued logic.
The problem canvas helps in identifying 4 Ws the key elements related to the problem. problem canvas is a part of ____
Correct answer: A. Problem scoping
The 4Ws problem canvas (Who, What, Where, Why) is used in problem scoping, the first stage of the AI project cycle.
Consider the following features of Neural networks.
A. It is essentially a machine learning algorithm.
B. It is useful when solving the problems for which the data set is very large.
C. They are able to extract features without input from the programmer.
D. These are systems modeled on the human brain and nervous system.
Correct answer: D. A, B, C & D
Neural networks are machine-learning models, excel with very large data sets, learn features automatically, and are loosely modelled on the brain. All four statements hold.
Consider the following draw backs is/are of Rule based approach is/are:
A. The learning is static.
B. Any changes made to the original data will not be considered.
C. Once trained the model cannot improve on the basis of feedback.
Correct answer: A. All the above statements are correct
Rule-based systems learn nothing after they are built: their knowledge is static, they ignore changes in the data, and they do not improve from feedback. All three are drawbacks.
Match List I with List II
Correct answer: B. A-II, B-II, C-I, D- II
Regression, KNN and decision trees learn from labelled examples (supervised). Clustering finds groups without labels (unsupervised).
Consider the graph given below. What is the order in which the nodes mentioned in the options are to be traversed to find the shortest path from A to Z using best first search?
A. Node-A
B. Node-B
C. Node-C
D. Node-D
E. Node-E
Choose the correct answer from the options given below:
Correct answer: A. A → C → F → D → E
Expanding the cheapest frontier node each time: A; C (2); F via C (2 + 3 = 5); D (6); E (6 + 2 = 8); then Z (12). So nodes are expanded in the order A → C → F → D → E.
Which of the following is related to function of layers in a neural network? → →
A. Information Input layer Hidden layer → →
B. Bias output layer hidden layer. → →
C. Hidden layer algorithm output layer. → →
D. Input layer output layer algorithms.
Correct answer: A. Only sequence ' A ' is correct.
Information flows from the input layer through the hidden layers to the output layer.
Given below are two statements: one is labelled as Assertion A and the other is labelled as
Reason R. A: Artificial Neural Networks are the backbone of deep learning algorithms. R. Back propagation is one of the techniques used to train an ANN. In the light of the above statements, choose the most appropriate answer from the options given below:
Correct answer: B. Both A and R are correct but R is NOT the correct explanation of A.
ANNs are the basis of deep learning, and backpropagation is one way to train them. Both are true, but training method does not explain why ANNs are the backbone of deep learning.
Overfitting is expected when we observe that?
Correct answer: B. With training iterations error on the training set decreases but the test set increases Q
Overfitting shows when training error keeps falling while test (validation) error starts rising: the model is memorizing noise.
The A* algorithm is optimal when,
Correct answer: A. It always finds the solution with the lowest total cost if the heuristic 'h' is admissible.
With an admissible heuristic (one that never overestimates), A* tree search finds a lowest-cost solution.
Which Artificial intelligence technique enables computers to understand the associations and relationships between objects & Events?
Correct answer: D. Pattern Matching
Pattern matching lets a system recognize associations and relationships between objects and events by matching them to known patterns.
Where does the values of alpha-beta search get updated?
Correct answer: A. Along the path of search.
α and β are updated as values are backed up along the path of the search, and passed down to the children.
Consider the following Learning algorithms.
I. Logistic regression.
II. Back propagation.
III. Linear regression.
IV. Forward propagation. Which of the following options represents classification algorithm? Q
Correct answer: C. I and II only
Logistic regression is a classifier, and backpropagation-trained neural networks are commonly used for classification. Linear regression predicts continuous values, and forward propagation is only a computation step.
Which Boolean operation on two variables can be represented by a single perception layer?
I. X1 AND X2 II.X1 OR X2
III. X1 NOR X2
IV. X1 XOR X2
Correct answer: C. I, II, and III only
AND, OR and NOR are linearly separable, so one perceptron layer can represent them. XOR is not linearly separable and needs a hidden layer.
Correct answer: D. a-II, b-II, c-II, d-I
Text planning, sentence planning and sentence generation (realization) are stages of natural language generation. Mapping input into useful representations is natural language understanding.
Choose the correct option describing the features of Artificial neural network
I. It is essentially machine learning algorithm.
II. It is useful when solving the problems for which the data set is very large.
III. They are able to extract features without input from the programmer. Iv. These are systems modeled on the human brain and nervous system
Correct answer: A. All the statements are correct.
ANNs are machine-learning models, suit very large data sets, extract features automatically, and are modelled on the nervous system. All four are correct.
Match List I with List II. List I: (A) Ontological engineering, (B) Taxonomy hierarchy, (C) Inheritance, (D) Probability models. List II: (I) Organizing subclass relations, (II) Organizing knowledge into categories and sub-categories, (III) Attaches a number to each possibility, (IV) Representing concepts, events, time and physical concepts of different domains.
Correct answer: D. (A)-(IV), (B)-(II), (C)-(I), (D)-(III)
Ontological engineering represents general concepts (events, time, physical objects) across domains; a taxonomy organizes categories and sub-categories; inheritance works through subclass relations; probability models attach a number to each possibility.
Statement I: "Grandparent is a parent of one's parent". Statement II: Its first-order predicate logic representation is ∀g, c grandparent(g, c) ⇔ ∃p parent(g, p) ∧ parent(p, c).
Correct answer: A. Both Statement I and Statement II are correct
g is a grandparent of c exactly when some p is a child of g and a parent of c. Both statements are correct.
Which agent deals with the happy and unhappy state?
Correct answer: A. Utility‐based agent
A utility-based agent rates states by how happy (useful) they are, not just goal or not-goal.
Given below are two statements
Statement I: Breadth‐First Search is optimal when all the step costs are equal whereas uniform‐cost search is optimal with any step‐cost.
Statement II: When all the step costs are same uniform‐cost search expends more nodes at depth d than the Breadth‐First Search. In light of the above statements, choose the correct answer from the options given below
Correct answer: A. Both Statement I and Statement II are true
BFS is optimal when all step costs are equal; uniform-cost search is optimal for any non-negative step costs. With equal costs UCS still expands the whole depth-d level before goal-testing, so it does more work than BFS. Both true.
Consider the game tree shown (root A is MAX; B and C are MIN; D, E, F, G are MAX with leaves D: 3, 5; E: 6, 9; F: 1, 2; G: 0, −1). Calculate the value at the root using alpha-beta pruning.
Correct answer: B. 5
D = 5, E = 9, so B = min(5, 9) = 5 and α = 5 at the root. F = 2, so C ≤ 2 < 5 and G is pruned. Root = max(5, ≤ 2) = 5.
Which among the following statement(s) is(are) FALSE?
A. Greedy best‐first search is not optimal but is often efficient. A*
B. is complete and optimal provided h(n) is admissible or consistent.
C. Recursive best‐first search is efficient in terms of time complexity but poor in terms of space complexity. h(n) = 0
D. is an admissible heuristic for the 8‐ puzzle.
Correct answer: C. C only
Recursive best-first search is efficient in space (linear) but may regenerate nodes, so it is poor in time; C states the opposite and is false. A, B and D are true (h = 0 never overestimates).
Consider the sentence: There is a country that borders both India and Pakistan. Which expression is correct, where Country(x) means x is a country and Border(x, y) means x and y share a border?
Correct answer: A. ∃c Country(c) ∧ Border(c, India) ∧ Border(c, Pakistan)
An existential is paired with ∧: some c is a country and borders both. Using ⇒ under ∃ (B) is satisfied by anything that is not a country.
Directions (Q56–60): A domain has three Boolean variables Toothache, Cavity and Catch, with full joint distribution: cavity ∧ toothache: catch 0.108, ¬catch 0.012; cavity ∧ ¬toothache: catch 0.072, ¬catch 0.008; ¬cavity ∧ toothache: catch 0.016, ¬catch 0.064; ¬cavity ∧ ¬toothache: catch 0.144, ¬catch 0.576.
The marginal probability of cavity P(cavity) is __________.
Correct answer: A. 0.200
P(cavity) = 0.108 + 0.012 + 0.072 + 0.008 = 0.200.
The probability of a cavity, given evidence of a toothache, P(cavity | toothache) is __________.
Correct answer: B. 0.600
P(toothache) = 0.108 + 0.012 + 0.016 + 0.064 = 0.2 and P(cavity ∧ toothache) = 0.12, so P(cavity | toothache) = 0.12/0.2 = 0.6.
