CS 580 FINAL EXAM QUESTIONS WITH CORRECT ANSWERS LATEST UPDATE 2026
Uncertainty - Answers the lack of knowledge or certainty about something
Belief state - Answers a set of possible world states
Contingency plan - Answers handles every possible eventuality that an agent's sensors may report
during execution
What does the right thing for an agent to do depend on? - Answers the relative importance of various
goals and the likelihood that, and degree to which they will be achieved
Logical agent - Answers believes each sentence to be true or false or has no opinion
Probabilistic agent - Answers may have a numerical degree of belief between 0 and 1
Probability - Answers the numerical measure of the likelihood that an event will occur
True or False: A logical agent may have a numerical degree of belief between 0 and 1. - Answers False,
this is true for a probabilistic agent.
Probabilistic reasoning - Answers applying the concept of probability to indicate uncertainty in
knowledge
Utility theory - Answers states that each state has a degree of utility, and that the agent will prefer
states with higher utility
Decision theory - Answers states that an agent is rational if and only if it chooses the action that
produces the highest expected utility, averaged over all the possible outcomes of the action
Baye's rule - Answers P(B|A) = P(A|B) * P(B) / P(A)
What probability quantifies a relationship in the causal direction? - Answers P(effect|cause)
What probability quantifies a relationship in the diagnostic direction? - Answers P(cause|effect)
What are the basic inference tasks that must be solved in a temporal model? - Answers filtering,
prediction, smoothing, and finding the most likely explanation
Filtering - Answers computing the belief state given all evidence to date
Prediction - Answers computing the posterior distribution over the future state given all evidence to
date
Smoothing - Answers computing the posterior distribution over a past state given all evidence to date
Recursive estimation - Answers computing the result for time t + 1 from the new evidence given the
result of filtering up to time t
Intelligent agents work through what 3 main components? - Answers sensors, actuators, and effectors
Sensor - Answers a device that detects changes in an environment
Actuator - Answers a component through which energy is converted into motion
Effector - Answers any device that affects the environment
When is an agent learning? - Answers if it improves its performance on future tasks after making
observations about the world
Improvements to an agent's performance depend on what 4 major factors? - Answers Which
component is to be improved, what prior knowledge the agent already has, what representation is
used for the data and the component, and what feedback is available to learn from
Inductive learning - Answers learning a general function or rule from specific input-output pairs
Deductive learning - Answers going from a known general rule to a new rule that is logically entailed
Unsupervised learning - Answers the agent learns patterns in the input even though no explicit
feedback is supplied
Reinforcement learning - Answers the agent learns from a series of reinforcements (rewards or
punishments)
Supervised learning - Answers the agent observes some example input-output pairs and learns a
function that maps from input to output
Semi-supervised learning - Answers the agent is given a few labeled examples and must make what it
can of a large collection of unlabeled examples
Learning - Answers a search through the space of possible hypotheses for one that will perform well
When does a hypothesis generalize well? - Answers if it correctly predicts the value of y for novel
examples
Consistent hypothesis - Answers a hypothesis which agrees with all of the data
Classification - Answers a supervised machine learning process of recognition, understanding, and
grouping of objects and ideas into preset categories
Regression - Answers When the target variable is continuous (such as tomorrow's temperature)
When is a learning problem realizable? - Answers if the hypothesis space contains the true function
Uncertainty - Answers the lack of knowledge or certainty about something
Belief state - Answers a set of possible world states
Contingency plan - Answers handles every possible eventuality that an agent's sensors may report
during execution
What does the right thing for an agent to do depend on? - Answers the relative importance of various
goals and the likelihood that, and degree to which they will be achieved
Logical agent - Answers believes each sentence to be true or false or has no opinion
Probabilistic agent - Answers may have a numerical degree of belief between 0 and 1
Probability - Answers the numerical measure of the likelihood that an event will occur
True or False: A logical agent may have a numerical degree of belief between 0 and 1. - Answers False,
this is true for a probabilistic agent.
Probabilistic reasoning - Answers applying the concept of probability to indicate uncertainty in
knowledge
Utility theory - Answers states that each state has a degree of utility, and that the agent will prefer
states with higher utility
Decision theory - Answers states that an agent is rational if and only if it chooses the action that
produces the highest expected utility, averaged over all the possible outcomes of the action
Baye's rule - Answers P(B|A) = P(A|B) * P(B) / P(A)
What probability quantifies a relationship in the causal direction? - Answers P(effect|cause)
What probability quantifies a relationship in the diagnostic direction? - Answers P(cause|effect)
What are the basic inference tasks that must be solved in a temporal model? - Answers filtering,
prediction, smoothing, and finding the most likely explanation
Filtering - Answers computing the belief state given all evidence to date
Prediction - Answers computing the posterior distribution over the future state given all evidence to
date
Smoothing - Answers computing the posterior distribution over a past state given all evidence to date
Recursive estimation - Answers computing the result for time t + 1 from the new evidence given the
result of filtering up to time t
Intelligent agents work through what 3 main components? - Answers sensors, actuators, and effectors
Sensor - Answers a device that detects changes in an environment
Actuator - Answers a component through which energy is converted into motion
Effector - Answers any device that affects the environment
When is an agent learning? - Answers if it improves its performance on future tasks after making
observations about the world
Improvements to an agent's performance depend on what 4 major factors? - Answers Which
component is to be improved, what prior knowledge the agent already has, what representation is
used for the data and the component, and what feedback is available to learn from
Inductive learning - Answers learning a general function or rule from specific input-output pairs
Deductive learning - Answers going from a known general rule to a new rule that is logically entailed
Unsupervised learning - Answers the agent learns patterns in the input even though no explicit
feedback is supplied
Reinforcement learning - Answers the agent learns from a series of reinforcements (rewards or
punishments)
Supervised learning - Answers the agent observes some example input-output pairs and learns a
function that maps from input to output
Semi-supervised learning - Answers the agent is given a few labeled examples and must make what it
can of a large collection of unlabeled examples
Learning - Answers a search through the space of possible hypotheses for one that will perform well
When does a hypothesis generalize well? - Answers if it correctly predicts the value of y for novel
examples
Consistent hypothesis - Answers a hypothesis which agrees with all of the data
Classification - Answers a supervised machine learning process of recognition, understanding, and
grouping of objects and ideas into preset categories
Regression - Answers When the target variable is continuous (such as tomorrow's temperature)
When is a learning problem realizable? - Answers if the hypothesis space contains the true function
