Paper 2 CS · UNIT 10 · MOCK TEST

Artificial Intelligence (AI) — Mock Test 1

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

0 / 25 answered 00:00

Q1. Consider the following neural network: input x₁ = 0.5 is connected to node A with weight 0.5; input x₂ = 0.6 is connected to node A with weight −0.8; input x₃ = 0.8 is connected to node A with weight 1; node A also receives a bias input of 0.5. Node A computes the net input y_in, which is then passed through node B (the activation function) to produce the final output y.
What will be the net input y_in and final output 'y' of this neural network given that the activation function is a threshold function defined as follows:
f(x) = 1 if x ≥ 1; f(x) = 0 if x < 1

Ay_in = 2.03, y = 1 By_in = 1.53, y = 1 Cy_in = 1.07, y = 1 Dy_in = 0.57, y = 0

Q2. A doctor knows that the disease Meningitis causes a patient to have a stiff neck say 70% of time. The doctor also knows some unconditional facts: the prior probability that any patient has Meningitis is 1/50,000 and the prior probability that any patient has a stiff neck is 1%. Letting s be the proposition that the patient has a stiff neck and m the proposition that the patient has meningitis, compute the probability P(m/s) using Bayes' rule.

A.014 B.0014 C.14 D.00014

Q3. Which of the following deals with the interaction between computers and humans using natural language?

APROLOG BELIZA CNLP DLISP

Q4. Classifying email as spam, labeling web pages based on their context, voice recognition are examples of which of the following?

AReinforcement learning BShortest Path Algorithm CSupervised learning DUnsupervised learning

Q5. Consider the following statements regarding Agent systems
A. Agent system comprises of an agent and an environment on which it acts
B. The controller part of an agent receives percepts from its body and sends commands to the environment
C. Agents act in the world through actuators which are non-noisy and always reliable.
D. The actuators of an agent convert stimuli into percepts
Choose the correct answer from the options given below:

AA, B Only BB, D Only CC, D Only DB, C, D Only

Q6. Consider the following steps used by a knowledge base designer to represent a world
A. Selects atoms to represent propositions
B. Ask questions about intended interpretation
C. Choose a task domain
D. Axiomatizing the domain
Choose the correct answer from the options given below:

AC → A → D → B BC → A → B → D CB → C → A → D DA → C → B → D

Q7. Match List I (GA termination criteria) with List II (description)

List I	List II
A. Worst Individual	I. At least half of the individuals will be better than or equal to the convergence value
B. Best Individual	II. Guarantees that virtually all individuals in the population will be within a particular fitness range
C. Sum of Fitness	III. Guarantees that the entire population is of a minimum standard
D. Median Fitness	IV. Faster search convergence, guaranteeing at least one best solution

AA → III, B → IV, C → II, D → I BA → IV, B → III, C → I, D → II CA → II, B → I, C → III, D → IV DA → II, B → III, C → IV, D → I

Q8. Consider the following table defining the sample inputs and corresponding target values for a perceptron model. What shall be the value of the updated weights after applying all the samples S1 to S4 (in the order S1, S2, S3, S4) to this model? Given that the initial weights w1 = 0, w2 = 0, learning rate = 0.1 and no bias is involved in the perceptron. The activation function is: y_observed = 1 if y_in > 0; 0 if y_in < 0.

Sample	x1	x2	target
S1	0	0	0
S2	0	1	1
S3	1	0	1
S4	1	1	1

Aw1 = 0.1, w2 = 0.1 Bw1 = 0.0, w2 = 0.2 Cw1 = 0.0, w2 = 0.1 Dw1 = 0.2, w2 = 0.2

Q9. Consider the following steps involved in the application of a Genetic algorithm for a problem
A. Select a pair of parents from the population
B. Apply mutation at each locus with probability pm
C. Calculate fitness of each member of the population
D. Apply crossover with probability pc to form offsprings
Choose the correct answer from the options given below describing the correct order of the above steps:

AA → C → B → D BC → A → D → B CC → A → B → D DA → D → B → C

Q10. Which of the following is NOT a parent selection technique used in genetic algorithm implementations?

ARadial BTournament CBoltzmann DRank

Q11. Match List I (Operations on Fuzzy Sets) with List II (Description)

List I	List II
A. Intersection	I. μA(x) + μB(x) − μA(x)·μB(x)
B. Bounded Sum	II. max(0, μA(x) − μB(x))
C. Bounded Difference	III. min(1, μA(x) + μB(x))
D. Algebraic Sum	IV. min(μA(x), μB(x))

AA → III, B → I, C → II, D → IV BA → III, B → II, C → IV, D → I CA → IV, B → III, C → II, D → I DA → II, B → I, C → III, D → IV

Q12. Which of the following is NOT a valid property over two fuzzy relations R̃ and S̃ which must be obeyed for performing λ-cut defuzzification?

A(R̃ ∪ S̃)_λ = R̃_λ ∪ S̃_λ B(R̃ ∩ S̃)_λ = R̃_λ ∩ S̃_λ C(complement of R̃)_λ ≠ complement of (R̃_λ) except when λ = 1 DFor any λ ≤ β, where 0 ≤ β ≤ 1, it is true that R_β ⊆ R_λ

Q13. Given that η refers to the learning rate and xᵢ refers to the iᵗʰ input to the neuron, which of the following most suitably describes the weight updation rule of a Kohonen SOM? (where 'j' refers to the jᵗʰ neuron in the lattice)

Aw_ij(new) = (1 − η) w_ij(old) + η · x_i Bw_ij(new) = η · w_ij(old) + (1 − η) · x_i Cw_ij(new) = (1 − η) w_ij(old) + x_i Dw_ij(new) = w_ij(old) + η · x_i

Q14. Consider the following statements regarding the STRIPS representation of a Planning problem
A. STRIPS is a Feature-centric representation
B. The features describing the state of the world are divided into Primitive and Derived
C. The STRIPS representation of an action comprises Precondition and Effect
D. STRIPS can directly define conditional effects.
Choose the correct answer from the options given below:

AA, C Only BB, C Only CA, D Only DB, C, D Only

Q15. Match List I with List II

List I	List II
A. Decision Tree	I. Delta Learning Rule
B. Supervised Learning	II. Self Organizing Map
C. Artificial Neural Network	III. C4.5 Algorithm
D. Instance Based Learning	IV. Non-linear Regression Algorithm

AA-I, B-II, C-III, D-IV BA-II, B-III, C-IV, D-I CA-III, B-IV, C-I, D-II DA-IV, B-I, C-II, D-III

Q16. Which of the following are correct for the neural network?
A. The training time depends upon the size of the network.
B. A neural network can be simulated on a conventional computer.
C. Neural networks mimic the same way as that of the human brain.
D. A neural network includes feedback.
Choose the correct answer from the options given below:

AA and B only BA, C and D only CA, B and C only DA and C only

Q17. What is the correct sequence of steps used in knowledge base design?
A. Ask questions about the intended interpretation.
B. Choose the task domain or world to represent.
C. Select atoms to represent propositions of interest.
D. Tell the system propositions that are true in the intended interpretation (axiomatizing the domain).
Choose the correct answer from the options given below:

AA, B, C, D BB, C, D, A CC, D, A, B DD, A, B, C

Q18. The mathematical notation to describe logical entailment of a sentence, "α entails another sentence β", is

Aα ⊨ β Bα ⊆ β Cβ ⊨ α Dβ ⊆ α

Q19. The kinds of symbols for basic syntactic elements of first-order logic are
A. Constant
B. Domain
C. Predicate
D. Temporal
E. Function
Choose the correct answer from the options given below:

AB, D only BA, B, C only CA, C, E only DC, D only

Q20. Which of the following is NOT a component of the classic Planning Definition?

AInit BDomain CAction DGoal

Q21. Definitions of ______ are organized into the following four categories: Thinking Humanly, Thinking Rationally, Acting Humanly, Acting Rationally

AMachine Learning BDeep Learning CArtificial Intelligence DNeural Network

Q22. Which one of the following is NOT related to feed-forward networks trained with the Backpropagation algorithm (in terms of the functions they can represent)?

ABoolean function BContinuous function CArbitrary function DGreedy function

Q23. Match List I with List II

List I	List II
(A) The activation	(I) is called the delta function rule.
(B) The learning method of perceptron	(II) is one of the key components of the perceptron, as in the most common neural network architecture.
(C) Areas of application of artificial neural network include	(III) is always boolean, like a switch.
(D) The output of the perceptron	(IV) system identification and control.

A(A)-(II), (B)-(IV), (C)-(III), (D)-(I) B(A)-(IV), (B)-(III), (C)-(II), (D)-(I) C(A)-(II), (B)-(I), (C)-(IV), (D)-(III) D(A)-(III), (B)-(IV), (C)-(II), (D)-(I)

Q24. Arrange the following steps in proper sequence involved in a Genetic Algorithm:
(A) Selection
(B) Initialization
(C) Crossover
(D) Mutation
(E) Evaluation
Choose the correct answer from the options given below:

A(A), (B), (C), (D), (E) B(E), (A), (B), (D), (C) C(B), (E), (A), (C), (D) D(A), (C), (B), (D), (E)

Q25. Arrange the following steps in proper sequence for the process of training a neural network.
(A) Weight initialization
(B) Feed forward
(C) Back Propagation
(D) Loss Calculation
(E) Weight Update
Choose the correct answer from the options given below:

A(A), (B), (D), (C), (E) B(D), (B), (A), (C), (E) C(A), (C), (D), (B), (E) D(E), (C), (B), (D), (A)