wgu D429 Intro to AI

artificial intelligence

machine driven, human-like intelligence and problem solving skills

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

NLP (national language processing)

a computers ability to communicate in human language

knowledge representation

that ability to store information.

automated reasoning

The computer’s ability to answer questions and draw new conclusions

machine learning

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

total turing test

evaluates a machines 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.

Example plant identification app: the app uses the camera to identify the plant.

robotics

the ability to manipulate and move objects

dualism

points to the existence of two distinct and independent realities; the body and the mind connects together.

empiricism (em-pier-ruh-cisim)

emphasizes knowledge acquisition through sensory experiences and observations

induction

involves drawing general conclusions from specific observations.

Example: I can see that a car can not move without wheels, so therefore I can conclude that all cars must use wheels to move.

ai observation sentence

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

legal positivism (think of laws)

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

AI must be used legally and follow the laws.

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.

think of deep learning… to find patterns and identify different things like NLP, etc.

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 perceived or viewed through the environment through its sensors.

Example: using a camera to acknowledge a human by speaking, or slamming on the brakes to avoid hitting a car (also an example of an agent function).;

Agents can:

sense, think, and decide, learn, plan, understand language, store knowledge, communicate, and work independently. (THIS IS A SCREENSHOT)

environment

the part that affects what an agent perceives.

actuators

a device that causes motion/movement.

precept

the content of an agents sensors.

precept sequence

the history of everything an agent has perceived

example: its a timeline of the what that specific agents has seen; ring timeline.

agent function

maps the precept sequence to actions.

slamming on brakes to avoid an object.

Type of Agents: (FROM THE SLIDESHOW)

Simple Reflex Agents - make choices based on what they see NOW.

Model-Based Reflex Agents - use the current environment to make choices.

Goal-based Reflex Agents - work towards achieving set goals via planning.

Utility-Based Agents- Think about goals AND (optimized) preferred outcomes. Look for the best-expected result.

Learning Agents - Learn from experience and get better with time.

task environment

specific setting or context in which an ai agent operates and performs its designated task

P.E.A.S.

performance, environment, actuators, sensors

software agent

a computer program that relates/acts for another user or a 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

example: a camera that use sensors at night

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.

it competes with itself and learns from those experiences to become better.

cooperative

allows single space occupancy

stays to itself; think of networks like a firewall everything stays in its own lane.

deterministic

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

everything is right in front of you and its already decided.

nondeterministic

when certain behaviors are unpredictable or unexpected

think of weather; its a chance of 50% snow but it is still unpredictable.

stochastic (stuh-ka-astic)

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.

think of this: episode connects with the show but it is still independent bc you can watch that episode without watching the whole show.

sequential

a concept where decisions affect future decisions.

static

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

dynamic

environments that consistently questions agents to make decisions and do nothing until agents make decisions.

constantly changing based on the environment until an agent makes a decision.

semi-dynamic

an environment that does not change with time despite an agents changing performance score

keeps going and does not change with time.

discrete

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

can not be counted; its too large.

digital technology

continuous

an environment where performed actions cannot be numbered.

waveform/analog (antennas) technology

known

an environment where the outcome of all actions is provided

unknown

a situation where the ai agent has little or 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.

It is influenced by its environment and context it operates in.

think of business ordering inventory. the amount of inventory depends on the customers and the size of the store (environment).

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 it environment, processes information, and takes action 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 behaviors

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; its ai's ability to understand, learn, and perform humanlike tasks

artificial superintelligence

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 individual 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 of their individual data without revealing their raw data to each other

event calculus

a way to describe and understand events and how they cause changes over time, helping computers figure out what happens when different actions take place

events

occurrences or actions that cause changes in the state of the world, typically described in terms of time and their effects on certain conditions or fluents.

time

treated as a discrete or continuous variable that allows you to represent and reason about temporal events

fluents

things that can change over time, like the temperature in a room or the status of a game, showing how events affect the world

objects

specific items or entities that exist in a situation, such as a car, a person, or a computer, which can interact with fluents and each other to create different outcomes

propositional attitudes

describes how agents relate to mental objects

modal logic

a system of logic that deals with modalities such as necessity and possibility, extending classical logic to include statements about what is necessarily or possibly true

modal operator

a symbol in modal logic used to qualify the truth of statements in terms of necessity or possibility

possible world

a hypothetical scenario or alternate reality used in modal logic to evaluate the truth of propositions under different conditions

accessibility relation

a relation in modal logic that links possible worlds, determining which world cans be considered when evaluating the truth of modal statements

linear temporal logic

a type of formal logic used to reason about sequences of events over time, where time is viewed as a linear progression

semantic network

a representation of knowledge inf the form of a graph, where nodes represent concepts or entities and edges represent relationships between them; used in fields like artificial intelligence and linguistics to model how information in interconnected

existential graphs

an early form of semantic network proposed by charles s. pierce that uses a visual format to represent logical relationships among objects and categories

multiple inheritance

a feature of semantic networks where an object can belong to multiple categories, potentially leading to complex inheritance patterns

procedural attachment

a technique in semantic networks where specific queries or assertions are handled by custom procedures rather than general inference algorithms, allowing for greater flexibility

default values

assumptions or general rules applied to categories in semantic networks, which can be overridden by more specific information when available.

overriding

the process of replacing default values with more specific information in semantic networks, ensuring that the network's information reflects known exceptions

description logics

a formal language used to define and combine categories with a focus on logical relationships and efficient reasoning about category definitions

subsumption

the process in description logics of determining whether one category is a subset of another by comparing their definitions

classification

the task in the description logics of determining whether an object belongs to a particular category based on its properties and category definitions

consistency

in description logics, the requirement that category definitions must be logically coherent and free from contradictions

tractability

refers to how manageable, solvable, or feasible a problem is

negation

the act of saying something is not true; the opposite of a statement, like "not X" meaning "X is false"

disjunction

the relationship between two ideas where one or the other can be true, like "X or Y" meaning either X is true, Y is true, or both are true