Artificial Intelligence Lecture Notes Flashcards

Vocabulary flashcards covering core topics from the Artificial Intelligence lecture notes, including definitions of AI types, ML paradigms, evolutionary phases, and readiness frameworks.

Artificial Intelligence (AI)

The capacity given by humans to machines to memorize, learn from experience, think, create, speak, judge, and make decisions; defined as the ability of machines to mimic human intelligence.

AI Success Factors

The three key factors required for successful AI implementation: high quality data, clear business objectives, and ethical responsibility.

AI Universe

The nested structural relationship of AI domains, starting from broad Artificial Intelligence, containing Machine Learning, which contains Neural Networks / Deep Learning, which encompasses Generative AI.

Machine Learning (ML)

A subset of AI that enables computers to learn from data and improve performance without being explicitly programmed for every situation, identifying patterns from historical data to make predictions.

Supervised Learning

A machine learning technique where the algorithm is trained on labeled datasets containing both input variables and corresponding outputs, utilizing classification and regression.

Unsupervised Learning

A type of machine learning where the model trains on unlabeled datasets without human supervision, using clustering and association to find hidden patterns and predict outputs.

Reinforcement Learning (RL)

A machine learning paradigm focused on how agents learn to maximize cumulative rewards by interacting with an environment through trial, feedback, action, and penalties.

Neural Network

An artificial group of interconnected neurons that learn from large amounts of data to recognize patterns, solve complex problems, and constantly adjust based on changing inputs.

Deep Learning (DL)

A machine learning approach using multilayered artificial neural networks to learn complex patterns from very large datasets, heavily used for image, speech, and natural language processing.

Turing Test

A test formulated by Alan Turing where a judge evaluates responses from a human and a machine; if the judge cannot distinguish the machine from the human, the AI passes.

Alan Turing

Historical figure known as the Father of Computer Science who proposed the Turing machine, helped break the German Enigma code in WWII, and introduced the Turing Test.

Rule-based System

The earliest AI systems (1950s-1980s) that execute predefined, hardcoded IF-THEN rules without learning from past transactions.

Expert System

An AI paradigm (1970s-1990s) designed to capture the knowledge of human experts in a knowledge base and apply predefined rules to solve specific domain problems.

Generative AI

AI systems emerging around 2022 that create entirely new content—such as text, images, video, audio, and code—based on user prompts or instructions.

Agentic AI

AI systems capable of autonomously pursuing goals by planning multi-step processes, using tools, making decisions, and taking actions with varying levels of human oversight.

AI Value Chain

The series of stages through which an organization generates business value using AI, consisting of four key components: Data, Algorithms, Infrastructure, and Decision Making.

Data (in AI)

The raw material of AI, comprising elements such as images, videos, audio, text, social media interactions, customer sales transactions, and employee records.

Algorithm (in AI)

Procedures and models (e.g., decision trees, linear regression, neural networks) used to process data, identify patterns, make predictions, or generate outputs.

Infrastructure (in AI)

The technical foundation required to store data, train models, run applications, and deliver results, including servers, GPUs, networks, databases, and cloud computing.

Traditional Automation

Technology designed to perform repetitive, predictable tasks automatically according to static, predefined rules without adapting or making dynamic decisions.

Narrow AI (ANI)

AI designed to perform a specific, restricted task without consciousness or general intelligence; also known as Weak AI.

General AI (AGI)

A hypothetical AI possessing human-level cognition that can understand, learn, and transfer knowledge across any task or domain with flexibility.

Super AI (ASI)

A speculative AI that would surpass human intelligence across all domains, including creativity, problem-solving, and social skills.

RAISE Framework

A diagnostic assessment framework for organizational AI readiness covering five dimensions: Resources, Ambition & strategy, Infrastructure, Skills & culture, and Ethics & governance.

Industry 4.0

The industrial phase focused on smart machines, data connectivity, cyber-physical systems, and digital automation.

Industry 5.0

The industrial phase centered on the collaboration between humans and intelligent machines, emphasizing human needs, sustainability, resilience, and circular economy practices.