Q#1: Uncertain knowledge arises when:
(A) Information about the world is incomplete or noisy
(B) Everything is fully known
(C) BFS nodes only
(D) DFS only
Answer: (A) Information about the world is incomplete or noisy
Q#2: Probabilistic reasoning represents:
(A) Degrees of belief in propositions
(B) Certain facts only
(C) BFS nodes only
(D) DFS only
Answer: (A) Degrees of belief in propositions
Q#3: Bayes’ theorem is used to:
(A) Update probabilities based on evidence
(B) Compute deterministic outcomes
(C) BFS nodes only
(D) DFS only
Answer: (A) Update probabilities based on evidence
Q#4: Conditional probability P(A|B) represents:
(A) Probability of A given B is true
(B) Probability of A independent of B
(C) BFS nodes only
(D) DFS only
Answer: (A) Probability of A given B is true
Q#5: A belief network (Bayesian network) represents:
(A) Probabilistic dependencies among variables
(B) Deterministic facts only
(C) BFS nodes only
(D) DFS only
Answer: (A) Probabilistic dependencies among variables
Q#6: Nodes in a Bayesian network represent:
(A) Random variables
(B) Actions only
(C) BFS nodes
(D) DFS only
Answer: (A) Random variables
Q#7: Directed edges in a Bayesian network represent:
(A) Conditional dependencies
(B) BFS nodes only
(C) DFS only
(D) Random assignments
Answer: (A) Conditional dependencies
Q#8: Joint probability distribution defines:
(A) Probability over all variables
(B) BFS nodes only
(C) DFS only
(D) Random values
Answer: (A) Probability over all variables
Q#9: Marginalization is:
(A) Summing out variables to compute probabilities of interest
(B) BFS nodes only
(C) DFS only
(D) Random assignments
Answer: (A) Summing out variables to compute probabilities of interest
Q#10: Conditional independence allows:
(A) Simplifying probabilistic reasoning
(B) BFS nodes only
(C) DFS only
(D) Random assignments
Answer: (A) Simplifying probabilistic reasoning
Q#11: D-separation in Bayesian networks is used to:
(A) Determine conditional independence
(B) BFS nodes only
(C) DFS only
(D) Random assignments
Answer: (A) Determine conditional independence
Q#12: Evidence in probabilistic reasoning refers to:
(A) Observed values of variables
(B) Unknown variables only
(C) BFS nodes
(D) DFS only
Answer: (A) Observed values of variables
Q#13: Probabilistic inference computes:
(A) Probability of query variables given evidence
(B) BFS nodes only
(C) DFS only
(D) Random assignments
Answer: (A) Probability of query variables given evidence
Q#14: Exact inference methods include:
(A) Variable elimination and belief propagation
(B) BFS only
(C) DFS only
(D) Random assignments
Answer: (A) Variable elimination and belief propagation
Q#15: Approximate inference methods include:
(A) Sampling methods like Monte Carlo
(B) Exact variable elimination
(C) BFS only
(D) DFS only
Answer: (A) Sampling methods like Monte Carlo
Q#16: Markov networks represent:
(A) Undirected probabilistic dependencies
(B) Directed dependencies only
(C) BFS nodes
(D) DFS only
Answer: (A) Undirected probabilistic dependencies
Q#17: Factor graphs are used to:
(A) Represent and compute joint probabilities efficiently
(B) BFS nodes only
(C) DFS only
(D) Random assignments
Answer: (A) Represent and compute joint probabilities efficiently
Q#18: Noisy-OR model is used for:
(A) Efficiently modeling multiple causes of an effect
(B) Deterministic outcomes only
(C) BFS nodes
(D) DFS only
Answer: (A) Efficiently modeling multiple causes of an effect
Q#19: Hidden Markov Models (HMMs) are used to:
(A) Model sequential probabilistic processes
(B) Single-step deterministic planning
(C) BFS only
(D) DFS only
Answer: (A) Model sequential probabilistic processes
Q#20: HMM states represent:
(A) Hidden variables of the system
(B) Observed variables only
(C) BFS nodes
(D) DFS only
Answer: (A) Hidden variables of the system
Q#21: Observations in HMMs are:
(A) Evidence dependent on hidden states
(B) Independent of states
(C) BFS nodes
(D) DFS only
Answer: (A) Evidence dependent on hidden states
Q#22: Belief update in HMM is performed using:
(A) Forward algorithm
(B) BFS only
(C) DFS only
(D) Random assignments
Answer: (A) Forward algorithm
Q#23: Filtering computes:
(A) Current belief state given past observations
(B) Future observations only
(C) BFS nodes
(D) DFS only
Answer: (A) Current belief state given past observations
Q#24: Prediction in HMM computes:
(A) Future state probabilities
(B) Past state probabilities only
(C) BFS nodes
(D) DFS only
Answer: (A) Future state probabilities
Q#25: Smoothing computes:
(A) Past state probabilities given all evidence
(B) Current state only
(C) BFS nodes
(D) DFS only
Answer: (A) Past state probabilities given all evidence
Q#26: Viterbi algorithm finds:
(A) Most probable sequence of hidden states
(B) BFS nodes only
(C) DFS only
(D) Random assignments
Answer: (A) Most probable sequence of hidden states
Q#27: Decision networks include:
(A) Chance nodes, decision nodes, and utility nodes
(B) Only chance nodes
(C) BFS nodes
(D) DFS only
Answer: (A) Chance nodes, decision nodes, and utility nodes
Q#28: Utility nodes represent:
(A) Preferences over outcomes
(B) Probabilities only
(C) BFS nodes
(D) DFS only
Answer: (A) Preferences over outcomes
Q#29: Influence diagrams are used to:
(A) Make decisions under uncertainty
(B) BFS nodes only
(C) DFS only
(D) Random assignments
Answer: (A) Make decisions under uncertainty
Q#30: Probabilistic reasoning is useful in AI for:
(A) Diagnosis, prediction, and decision-making
(B) Deterministic actions only
(C) BFS only
(D) DFS only
Answer: (A) Diagnosis, prediction, and decision-making
Q#31: Common assumptions in uncertain reasoning include:
(A) Independence or conditional independence of variables
(B) Complete determinism
(C) BFS only
(D) DFS only
Answer: (A) Independence or conditional independence of variables
Q#32: Bayes’ rule can be used to compute:
(A) Posterior probability
(B) Prior only
(C) BFS nodes
(D) DFS only
Answer: (A) Posterior probability
Q#33: Prior probability represents:
(A) Belief before observing evidence
(B) Belief after evidence
(C) BFS nodes
(D) DFS only
Answer: (A) Belief before observing evidence
Q#34: Likelihood represents:
(A) Probability of evidence given hypothesis
(B) Prior probability
(C) BFS nodes
(D) DFS only
Answer: (A) Probability of evidence given hypothesis
Q#35: Posterior probability is:
(A) Updated belief after considering evidence
(B) Prior only
(C) BFS nodes
(D) DFS only
Answer: (A) Updated belief after considering evidence
Q#36: Probabilistic reasoning handles:
(A) Uncertainty, noise, and partial information
(B) Fully deterministic information
(C) BFS only
(D) DFS only
Answer: (A) Uncertainty, noise, and partial information
Q#37: Approximate inference methods include:
(A) Sampling, particle filtering
(B) Variable elimination only
(C) BFS only
(D) DFS only
Answer: (A) Sampling, particle filtering
Q#38: Particle filtering is used to:
(A) Estimate belief states in dynamic systems
(B) Static deterministic systems only
(C) BFS only
(D) DFS only
Answer: (A) Estimate belief states in dynamic systems
Q#39: Probabilistic graphical models include:
(A) Bayesian networks and Markov networks
(B) BFS nodes only
(C) DFS only
(D) Random assignments
Answer: (A) Bayesian networks and Markov networks
Q#40: Real-world applications of uncertain reasoning include:
(A) Robot localization, medical diagnosis, speech recognition
(B) Deterministic scheduling only
(C) BFS only
(D) DFS only
Answer: (A) Robot localization, medical diagnosis, speech recognition
Q#41: Independence assumptions reduce:
(A) Complexity of probabilistic computations
(B) BFS nodes only
(C) DFS only
(D) Random assignments
Answer: (A) Complexity of probabilistic computations
Q#42: Decision-making under uncertainty requires:
(A) Probabilities and utilities
(B) Deterministic plans only
(C) BFS only
(D) DFS only
Answer: (A) Probabilities and utilities
Q#43: Conditional probability tables (CPTs) store:
(A) Probability of variable given parents
(B) Random values only
(C) BFS nodes
(D) DFS only
Answer: (A) Probability of variable given parents
Q#44: Exact inference is feasible for:
(A) Small or sparsely connected networks
(B) Large, dense networks only
(C) BFS only
(D) DFS only
Answer: (A) Small or sparsely connected networks
Q#45: Approximate inference is needed for:
(A) Large or highly connected networks
(B) Small networks only
(C) BFS only
(D) DFS only
Answer: (A) Large or highly connected networks
Q#46: Utility theory is used to:
(A) Choose best action under uncertainty
(B) Only compute probabilities
(C) BFS only
(D) DFS only
Answer: (A) Choose best action under uncertainty
Q#47: Expected utility combines:
(A) Probabilities and utilities of outcomes
(B) BFS nodes only
(C) DFS only
(D) Random assignments
Answer: (A) Probabilities and utilities of outcomes
Q#48: Uncertain reasoning supports:
(A) Diagnosis, prediction, planning, and decision-making
(B) Deterministic problems only
(C) BFS only
(D) DFS only
Answer: (A) Diagnosis, prediction, planning, and decision-making
Q#49: Knowledge representation for uncertain reasoning allows:
(A) Efficient probabilistic inference
(B) Only deterministic reasoning
(C) BFS only
(D) DFS only
Answer: (A) Efficient probabilistic inference
Q#50: The main goal of uncertain knowledge and reasoning is:
(A) Make rational decisions in the presence of uncertainty
(B) BFS nodes only
(C) DFS only
(D) Random assignments
Answer: (A) Make rational decisions in the presence of uncertainty