Introduction to Artificial Intelligence: Basics to Intelligent Agents

Comprehensive vocabulary flashcards covering basic AI concepts, history, classifications, machine learning types, and intelligent agent-environment interactions.

Artificial Intelligence (AI)

A branch of computer science that develops systems capable of performing tasks that normally require human-like intelligent abilities, such as learning, recognizing patterns, understanding language, solving problems, and making decisions.

Turing Test

A test of machine intelligence based on the 'Imitation Game' proposed by Alan Turing in 1950.

Dartmouth Workshop

A 1956 workshop that helped establish Artificial Intelligence as a formal academic research field.

Expert Systems

An AI approach from the 1980s that became an important commercial application of artificial intelligence by using predefined rules and knowledge bases.

IBM Deep Blue

An AI chess computer that defeated world chess champion Garry Kasparov in 1997.

Generative AI

Advanced AI systems and foundation models emerging widely in the 2020s capable of producing text, images, audio, and code.

Weak AI / Narrow AI

AI systems designed for one task or a limited range of related tasks, where 'weak' refers strictly to the narrow scope of the system rather than its performance level.

Strong AI / Artificial General Intelligence (AGI)

A theoretical concept describing a machine with broad, human-level intelligence that can learn, reason, adapt, and transfer knowledge across many different tasks.

Reactive Machines

AI systems that respond only to the current input or situation and do not store or use a memory of past experiences when making decisions.

Limited Memory AI

AI systems that use information from previous observations or historical data to make decisions for a specific task, representing most modern machine-learning applications.

Theory of Mind AI

A hypothetical capability in AI to understand, model, and reason about human mental states, including beliefs, knowledge, intentions, and emotions.

Self-Aware AI

A hypothetical level of AI in which a machine would possess consciousness, self-awareness, and knowledge of its own internal state.

Augmented Intelligence

Technology designed to assist, support, and enhance human capability and decision-making rather than fully replace human involvement.

Cognitive Computing

A broad term for computing systems designed to assist humans with perception, reasoning, learning, and interaction.

Machine Learning (ML)

A subfield of AI where algorithms learn patterns from data and examples instead of requiring explicit, manually written rules for every situation.

Supervised Learning

A machine learning method that learns from labeled examples, commonly divided into classification (predicting a category) and regression (predicting a numerical value).

Unsupervised Learning

A machine learning method that finds patterns, groupings, or structures in data without relying on predefined target labels.

Reinforcement Learning

A machine learning approach where an agent learns to make a sequence of decisions by interacting with an environment through trial and error, using rewards and penalties.

Deep Learning

A specialized branch of Machine Learning based primarily on multi-layer neural networks that learn numerical parameters from complex data such as images, speech, and text.

Perception

The component of intelligence responsible for receiving and sensing raw information from the environment.

Intelligent Machine

A system—either software-only or physical—designed to perceive information, process it, and select actions to achieve a specific goal.

Agent

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

Environment

Everything outside of an agent that the agent can perceive through sensors or influence through actions.

Percept

The specific sensory information or inputs received by an agent from the environment at a particular point in time.

Rational Agent

An agent that selects an action expected to achieve the best outcome according to its performance measure, even under incomplete information or uncertainty.

Performance Measure

The objective criterion used to evaluate how successfully an agent accomplishes its task.

Fully Observable vs. Partially Observable Environment

An environmental classification based on whether an agent's sensors give complete access to the state of the environment at each point in time or only partial information.

Deterministic vs. Stochastic Environment

An environmental classification based on whether the next state of the environment is completely determined by the current state and action, or involves uncertainty and randomness.

Static vs. Dynamic Environment

An environmental classification based on whether the environment can change while the agent is deliberating and deciding on an action.

Discrete vs. Continuous Environment

An environmental classification based on whether states, time, percepts, and actions consist of a finite number of distinct values or vary smoothly along continuous scales.