CSC 424 Artificial Intelligence Revision Flashcards

Comprehensive vocabulary flashcards for CSC 424, covering the definitions of AI, agent types, search algorithms, and natural language processing components.

Artificial Intelligence

A branch of computer science that is concerned with designing intelligent agents that perceive their environment.

Weak AI

AI designed to perform one specific task.

Strong AI

AI that can perform intellectual tasks that humans can do.

Super AI

AI that is more intelligent than humans.

Agent

An entity that perceives the environment through sensors and acts upon the environment through actuators.

Sensor

A device used to perceive the environment.

Actuator

A device used to perform actions.

Agent function

A mapping that tells the agent what action to take for every possible percept history.

Rational agent

An agent that chooses the action that maximizes the expected value of its performance measure based on available information.

Performance measure

A standard that evaluates how successful an agent is.

PEAS

A framework for specifying an agent's task environment, standing for Performance measure, Environment, Actuators, and Sensors.

Simple reflex agent

An agent that reacts using if-then rules in predictable settings.

Model-based reflex agent

An agent that uses memory to handle incomplete data about the environment.

Goal-based agent

An agent that chooses actions specifically to achieve defined goals.

Utility-based agent

An agent that picks actions based on the best overall value or utility.

Learning agent

An agent that improves its performance by learning from past experiences.

Search

The process of exploring possible states in order to find a path from an initial state to a goal state.

State space

The set of all possible states that can be reached from the initial state.

Path cost

The total cost associated with reaching the goal state.

Optimal solution

A solution that has the least cost among all possible solutions.

State space graph

A mathematical representation of a search problem where nodes represent states.

Search tree

A diagram showing how a search algorithm explores the state space, starting from a root node.

Breadth-first search (BFS)

A search algorithm that explores all nodes at one level before moving to the next level, using a FIFO (First-In-First-Out) queue.

Depth-first search (DFS)

A search algorithm that explores one branch completely before backtracking, using a LIFO (Last-In-First-Out) stack.

Uniform cost search (UCS)

A search algorithm that expands the node with the lowest path cost first, using a priority queue.

Completeness

The property of a search algorithm that guarantees finding a solution if one exists.

Optimality

The property of an algorithm that ensures it always finds the best or least-cost solution.

Time complexity

A measure of how much time a search algorithm takes to find a solution.

Space complexity

A measure of how much memory an algorithm requires during its search process.

Natural Language Processing (NLP)

A branch of AI that enables computers to understand, interpret, and generate human language.

Natural language understanding (NLU)

A component of NLP that focuses on understanding what a person means.

Natural language generation (NLG)

A component of NLP that focuses on producing human-like responses.

Tokenization

The process of breaking texts into smaller units called tokens.

Stemming

The process of removing prefixes or suffixes from words to provide a root word.

Lemmatization

The process of converting words into their proper dictionary form.

NLTK

The Natural Language Toolkit, a popular Python library for natural language processing tasks.