GATE DA Artificial Intelligence – Full Mock Test-1 ⋆ CSE Study247

GATE DA Artificial Intelligence – Full Mock Test-1

Questions 91-95 of 100

0% completed (0/100 answered)

Question 91

MSQ · Multiple Correct 2 mark

Which of the following statements regarding D-SEPARATION in Bayesian Networks are CORRECT?

A A chain path A -> B -> C is BLOCKED if B is in the evidence set. B A fork path A <- B -> C is BLOCKED if B is in the evidence set. C A collider path A -> B <- C is BLOCKED if NEITHER B nor any descendant of B is in the evidence set. D A collider path A -> B <- C is OPEN if B is in the evidence set.

Question 92

MSQ · Multiple Correct 2 mark

Select the CORRECT statements regarding APPROXIMATE INFERENCE algorithms:

A Prior Sampling generates unweighted samples directly from the joint prior. B Rejection Sampling discards samples that do not match observed evidence. C Likelihood Weighting uses weighted samples to avoid sample rejection. D Gibbs Sampling is a Markov Chain Monte Carlo (MCMC) technique.

Question 93

MSQ · Multiple Correct 2 mark

Which variables belong to the MARKOV BLANKET of a target node X in a Bayesian Network?

A X's Parents B X's Children C Other parents of X's children (Spouses) D X's Grandparents

Question 94

MSQ · Multiple Correct 2 mark

Which of the following are VALID properties of Bayes' Theorem and Probability?

Question 95

MSQ · Multiple Correct 2 mark

Which techniques can be used for EXACT INFERENCE in Bayesian Networks?

A Variable Elimination B Junction Tree Algorithm (Belief Propagation) C Enumeration / Full Joint Summation D Rejection Sampling