CS 430: Survey of AI - Chapter 12: Quantifying Uncertainty

These flashcards cover key concepts related to quantifying uncertainty in AI, including definitions and explanations of uncertainty, probability distributions, and decision-making frameworks.

Uncertainty

The state of being unsure or having doubts about something, prevalent in real-world scenarios involving incomplete information.

Partial observability

A situation where not all aspects of the environment are known, affecting decision-making.

Probabilistic assertions

Statements that summarize the effects of ignorance and laziness using probabilities.

Decision theory

A framework that combines probability theory and utility theory to make rational choices.

Random variable

A variable that represents an uncertain quantity, usually defined as a function of possible outcomes.

Probability distribution

A mathematical function that provides the probabilities of occurrence of different possible outcomes.

Marginal distribution

A distribution obtained by summing out one or more variables from a joint distribution.

Conditional probability

The probability of an event occurring given that another event has already occurred.

Bayes' Rule

A rule that describes how to update the probability of a hypothesis as more evidence becomes available.

Independence

Two events are independent if the occurrence of one does not affect the probability of the other.

Conditional independence

A condition where two variables are independent given the knowledge of a third variable.

Naïve Bayes model

A probabilistic model that assumes independence among predictors, used for classification.

Uncertainty

The state of being unsure or having doubts about something, prevalent in real-world scenarios involving incomplete information.

Partial observability

A situation where not all aspects of the environment are known, affecting decision-making.

Probabilistic assertions

Statements that summarize the effects of ignorance and laziness using probabilities.

Decision theory

A framework that combines probability theory and utility theory to make rational choices.

Random variable

A variable that represents an uncertain quantity, usually defined as a function of possible outcomes.

Probability distribution

A mathematical function that provides the probabilities of occurrence of different possible outcomes.

Marginal distribution

A distribution obtained by summing out one or more variables from a joint distribution.

Conditional probability

The probability of an event occurring given that another event has already occurred.

Bayes' Rule

A rule that describes how to update the probability of a hypothesis as more evidence becomes available.

Independence

Two events are independent if the occurrence of one does not affect the probability of the other.

Conditional independence

A condition where two variables are independent given the knowledge of a third variable.

Naïve Bayes model

A probabilistic model that assumes independence among predictors, used for classification.

Expected value

The average or mean value of a random variable, calculated as the sum of all possible outcomes, each multiplied by their probabilities.

Variance

A measure of the dispersion of a set of values, representing how far each number in the set is from the mean.

Standard deviation

The square root of the variance, indicating the amount of variation or dispersion in a set of values.

Joint distribution

A probability distribution that models two or more random variables simultaneously.

Likelihood

The measure of how well a statistical model explains a set of data, often related to the probability of observing the given data under the model.

Markov decision process (MDP)

A mathematical framework for modeling decision-making in scenarios where outcomes are partly random and partly under the control of a decision maker.

Uncertainty

The state of being unsure or having doubts about something, prevalent in real-world scenarios involving incomplete information.

Partial observability

A situation where not all aspects of the environment are known, affecting decision-making.

Probabilistic assertions

Statements that summarize the effects of ignorance and laziness using probabilities.

Decision theory

A framework that combines probability theory and utility theory to make rational choices.

Random variable

A variable that represents an uncertain quantity, usually defined as a function of possible outcomes.

Probability distribution

A mathematical function that provides the probabilities of occurrence of different possible outcomes.

Marginal distribution

A distribution obtained by summing out one or more variables from a joint distribution.

Conditional probability

The probability of an event occurring given that another event has already occurred.

Bayes' Rule

A rule that describes how to update the probability of a hypothesis as more evidence becomes available.

Independence

Two events are independent if the occurrence of one does not affect the probability of the other.

Conditional independence

A condition where two variables are independent given the knowledge of a third variable.

Naïve Bayes model

A probabilistic model that assumes independence among predictors, used for classification.

Expected value

The average or mean value of a random variable, calculated as the sum of all possible outcomes, each multiplied by their probabilities.

Variance

A measure of the dispersion of a set of values, representing how far each number in the set is from the mean.

Standard deviation

The square root of the variance, indicating the amount of variation or dispersion in a set of values.

Joint distribution

A probability distribution that models two or more random variables simultaneously.

Likelihood

The measure of how well a statistical model explains a set of data, often related to the probability of observing the given data under the model.

Markov decision process (MDP)

A mathematical framework for modeling decision-making in scenarios where outcomes are partly random and partly under the control of a decision maker.

Fill in the blank: The ____ is the average or mean value of a random variable.

Expected value

Fill in the blank: A variable that represents an uncertain quantity is known as a ____.

Random variable

Fill in the blank: Bayes' Rule helps to update the probability of a ____ as more evidence becomes available.

hypothesis

Fill in the blank: The ____ of a set is a measure of dispersion indicating how far each number is from the mean.

Variance

True or False: Two events are independent if the occurrence of one does not affect the probability of the other.

True

True or False: Conditional independence means two variables are dependent given a third variable.

False