WGU D429 - Key Terms

artificial intelligence (AI)

machine-driven, human-like intelligence and problem-solving systems

intelligence

the ability to understand, apply knowledge, and solve complex problems

rationality

the ability to make sound decisions

Turing test

a thought experiment that decides a computer's ability to respond as a human

natural language processing

a computer's ability to communicate in human language

knowledge representation

the ability to store information

automated reasoning

the computer's ability to answer questions and draw new conclusions

machine learning (ML)

the field of study that gives computers the ability to learn from data without being explicitly programmed

total Turing test

evaluates a machine's intelligence by assessing its ability to not only communicate in natural language but also perceive and interact with the physical world and become indistinguishable from a human

computer vision

a field of computer science that focuses on enabling computers to find and understand objects and people in images and videos

robotics

the ability to manipulate and move objects

dualism

posits the existence of two distinct and independent realities

empiricism

emphasizes knowledge acquisition through sensory experiences and observations

induction

involves drawing general conclusions from specific observations

AI observation sentence

a statement generated by an AI system based on its analysis of data, reflecting the AI's interpretation of observed patterns or trends

legal positivism

a theory of laws where rules are created by humans and valid based on legitimate authority

neural networks

computational models inspired by the human brain, consisting of interconnected layers of nodes that process and learn from data to recognize patterns and make predictions

ethical artificial intelligence

considers that the study and use of AI technologies should follow ethical rules to ensure fairness, transparency, and accountability

agent

anything that can be viewed as perceiving its environment through sensors

environment

the part that affects what an agent perceives

actuators

a device that causes motion (robotic movement)

percept

the content of an agent's sensors

percept sequence

the history of everything an agent has perceived

agent function

maps percept sequence to actions

task environment

specific setting or context in which an AI agent operates and performs its designated tasks

PEAS

performance, environment, actuators, sensors

software agent

a computer program that acts for another user or program in a relationship with an agent

softbot

a program that issues commands within a software environment and interprets feedback

fully observable

occurs when sensors detect all aspects that are relevant to the choice of an action

partially observable

occurs when parts of a state are missing from sensor data

unobservable

when an agent has no sensors

single agent

one agent performing a task

multiagent

when two or more agents perform a task together

competitive

maximizes agent performance measures by avoiding the pitfalls of predictability

cooperative

allows single-space occupancy

deterministic

when the state of an environment is completely decided by the current state and action executed by an agent

nondeterministic

when certain behaviors are unpredictable or unexpected

stochastic

when the model of an environment explicitly deals with probabilities

episodic

a process where agents do not think ahead but base decisions on current issues

sequential

a concept where decisions affect future decisions

static environment

an environment that remains unchanged while an agent is deliberating or acting

dynamic environment

environments that consistently question agents to make decisions and do nothing until agents make decisions

semi-dynamic environment

an environment that does not change with time despite an agent's changing performance score

discrete

a system that models problems that are too large to be continuous

continuous

an environment where performed actions cannot be numbered

known

an environment where the outcome of all actions is provided

unknown

a situation where the AI agent has little or no prior knowledge about the environment it is operating in

environment class

a category or grouping in programming that encapsulates environmental variables and settings, allowing for the management and configuration of application behavior based on the specific context in which it operates

smart agent

a software program capable of performing tasks autonomously, learning from its environment, and making decisions or taking actions to achieve specific goals

AI agent

a software entity that perceives its environment, processes information, and takes actions autonomously to achieve a specific objective

learning agents

the agents that handle making improvements

performance element

selects external actions

critic

decides performance element modifications

problem generator

suggests actions that lead to new and informative experiences

reward

provides direct feedback on the quality of agent behavior

penalty

provides critical feedback on agent behavior

training data

a set of examples used to teach a machine learning model, allowing it to learn patterns and make predictions or decisions

operational data

information generated during the regular functioning of a system, used for monitoring, managing, and improving ongoing operations

human-level AI

commonly referred to as artificial general intelligence (AGI); is AI's ability to understand, learn, and perform humanlike tasks

artificial superintelligence (ASI)

refers to the future of AI, which could potentially surpass all levels of human intelligence

gorilla problem

refers to apprehension about creating superintelligent machines

King Midas problem

describes a hypothetical scenario or challenge that arises when designing intelligent systems that optimize for a specific objective without considering the broader consequences or trade-offs

assistance game

occurs when a machine tries to achieve a human objective

inverse reinforcement learning

occurs when machines learn about human preferences by observing human choices

AI ethics

the examination of moral issues related to the development and use of artificial intelligence, including fairness, transparency, and societal impact

negative side effects

the harmful effects that technologies have on the world

surveillance cameras

recording devices that capture movement

cybersecurity

the practice of protecting computer systems, networks, and digital data from unauthorized access, attacks, damage, or theft

de-identification

the process of removing identifying information

generalizing fields

a form of minimizing risks by minimizing information

k-anonymity

indistinguishable database

aggregate querying

processes the data from multiple indexed entities to return a single summary value

differential privacy

a mathematical framework that ensures the privacy of individuals in a dataset by providing guarantees that the inclusion or exclusion of any single individual's data does not significantly affect the outcome of any analysis, thereby protecting personal information from being revealed

federated learning

often referred to as collaborative learning, this is a decentralized approach to training machine learning models that does not require an exchange of data from client devices, thereby ensuring privacy

secure aggregation

a privacy-preserving technique that allows multiple parties to collaboratively compute an aggregate value (e.g., a sum or average) of their individual data without revealing their raw data to each other

probabilistic inference

deduction of probabilities from known data using probabilistic models

Bayes' rule

also known as Bayes' theorem, uses prior knowledge or beliefs (prior probabilities) with new data or observations to calculate revised probabilities (posterior probabilities)

query

a request for information or the probability of an event within a probabilistic model

marginal probability

the probability of a single event occurring, obtained by summing or integrating over other variables

marginalization

the process of summing or integrating out unneeded variables to compute marginal probabilities

normalization

adjusting probabilities so that their total sums to one

marginal independence

when two variables are independent without conditioning on any other variables

conditional independence

when two variables are independent given the knowledge of a third variable

Naive Bayes

a classification algorithm based on Bayes' theorem with strong independence assumptions

Naive Bayes model

probability distribution model where the effect variables are not strictly independent of the given cause variable

Bayesian classifier

a probabilistic model that classifies data based on Bayes' theorem, using prior knowledge and evidence to predict the likelihood of different outcomes

sybil

a single entity that creates multiple identities to gain an unfair advantage or manipulate a system, often seen in online platforms and networks

sybil attack

occurs when an attacker creates multiple fake identities or nodes to disrupt or gain control over a network, influencing decisions or overwhelming resources

existence uncertainty

refers to the lack of certainty about whether a particular entity or event exists within a given context or model

identity uncertainty

involves not knowing the identity of an individual or entity, often due to incomplete or ambiguous information

open-universe probability model (OUPM)

a framework used to handle situations where the set of possible outcomes or entities is not fixed and can change over time as new information is introduced

Bayesian inference

a method of updating the probability of a hypothesis or event based on new evidence or information

number statement

a statement that provides specific quantitative information, such as a count or measurement, about a particular variable or phenomenon

Poisson distribution

a probability distribution that describes the likelihood of a given number of events occurring within a fixed interval of time or space

discrete log-normal distribution

a probability distribution for a random variable whose logarithm is normally distributed, often used to model phenomena with multiplicative effects and where the variable takes on discrete values

order-of-magnitude distribution

describes the distribution of values based on their scale or size, often using logarithmic scales to analyze data that spans several orders of magnitude

number variables

variables that represent quantitative values or counts, as opposed to categorical or qualitative data

random variables

variables whose values are subject to randomness or uncertainty and are typically used in probability and statistics to model and analyze random processes

generative program

software that autonomously creates new content or data, such as text, images, or designs, often using algorithms or AI

grammar

a collection of rules that specify how phrases can be organized in a structured way, often represented as a tree-like diagram