AI Glossary
Commonly used terms in AI from A to Z with definitions
Related: AI Acronyms | FAQs | Books
Whether you're preparing for an exam, an interview, or just want to know more about AI, it's good to know common industry terms and concepts. This list of AI words provides an overview of key concepts in AI and related topics. Links are provided to AI World pages in case you want to learn more about a topic.
A
AI ethics: AI ethics refers to the issues that AI stakeholders such as engineers and government officials must consider to ensure that the technology is developed and used responsibly. This means adopting and implementing systems that support a safe, secure, unbiased, and environmentally friendly approach to artificial intelligence.
Algorithm: A set of rules or instructions given to an AI system to help it learn and perform tasks.
Artificial General Intelligence (AGI): A type of AI that can understand, learn, and apply knowledge across a wide range of tasks at a human-like level.
Artificial Intelligence (AI): The simulation of human intelligence in machines programmed to perform tasks that typically require human intelligence.
Artificial Neural Network (ANN): A computational model inspired by the human brain, used in machine learning to recognize patterns and solve problems.
Application programming interface (API): An API, or application programming interface, is a set of protocols that determine how two software applications will interact with each other. APIs tend to be written in programming languages such as C++ or JavaScript.
B
Bias: In AI, bias refers to systematic errors or unfairness in a model's predictions, often due to skewed training data or flawed assumptions.
Big Data: Extremely large datasets that can be analyzed computationally to reveal patterns, trends, and insights.
C
Chatbot: A program designed to simulate conversation with human users, often powered by AI.
Computer Vision: A field of AI that enables machines to interpret and understand visual information from the world.
Cognitive Computing: A subset of AI that aims to mimic human thought processes in complex situations.
D
Data Mining: The process of discovering patterns and knowledge from large amounts of data.
Deep Learning: A subset of machine learning that uses multi-layered neural networks to analyze complex data.
Data science: Data science is an interdisciplinary field of technology that uses algorithms and processes to gather and analyze large amounts of data to uncover patterns and insights that inform business decisions.
Dataset: A collection of data used to train or evaluate AI models.
E
Emergent behavior: Emergent behavior, also called emergence, is when an AI system shows unpredictable or unintended capabilities.
Expert System: An AI system designed to mimic the decision-making abilities of a human expert in a specific domain.
Explainable AI (XAI): AI systems designed to provide clear and understandable explanations for their decisions and actions.
F
Feature Extraction: The process of identifying and selecting relevant information from raw data to improve model performance.
Fuzzy Logic: A form of logic that deals with approximate reasoning rather than fixed and exact values.
G
Generative AI: AI models that can generate new content, such as text, images, or music, based on training data.
GPT (Generative Pre-trained Transformer): A type of language model that uses deep learning to generate human-like text.
Guardrails: Guardrails refers to restrictions and rules placed on AI systems to make sure that they handle data appropriately and don't generate unethical content.
H
Hallucination: Hallucination refers to an incorrect response from an AI system, or false information in an output that is presented as factual information.
Heuristic: A rule-of-thumb or shortcut used by AI systems to solve problems more efficiently.
Hyperparameter: A parameter set before the learning process begins, which influences how the model is trained.
I
Image recognition: Image recognition is the process of identifying an object, person, place, or text in an image or video.
Inference: The process of using a trained AI model to make predictions or decisions based on new data.
Internet of Things (IoT): A network of interconnected devices that collect and exchange data, often used in AI applications.
J
Joint Probability: A measure used in AI to calculate the likelihood of two events occurring simultaneously.
K
Knowledge Graph: A structured representation of knowledge that helps AI systems understand relationships between entities.
K-Nearest Neighbors (KNN): A simple machine learning algorithm used for classification and regression tasks.
L
Large Language Model (LLM): A type of AI model trained on vast amounts of text data to understand and generate human language.
Learning Rate: A hyperparameter that determines how quickly an AI model adjusts its parameters during training.
Limited memory: Limited memory is a type of AI system that receives knowledge from real-time events and stores it in the database to make better predictions.
M
Machine Learning (ML): A subset of AI that enables systems to learn and improve from experience without being explicitly programmed.
Model: A mathematical representation of a real-world process created by an AI system.
N
Natural Language Processing (NLP): A field of AI focused on enabling machines to understand, interpret, and generate human language.
Neural Network: A computational model inspired by the human brain, used in deep learning.
O
Overfitting: A problem in machine learning where a model performs well on training data but poorly on new, unseen data.
Optimization: The process of adjusting a model's parameters to minimize errors and improve performance.
P
Pattern recognition: Pattern recognition is the method of using computer algorithms to analyze, detect, and label regularities in data. This informs how the data gets classified into different categories.
Predictive Analytics: The use of data, statistical algorithms, and machine learning techniques to predict future outcomes.
Prompt: A text input given to an AI model to generate a response or perform a task.
Q
Quantum Computing: A type of computing that uses quantum-mechanical phenomena, potentially revolutionizing AI by solving complex problems faster.
R
Reinforcement Learning: A type of machine learning where an agent learns by interacting with an environment and receiving rewards or penalties.
Robotics: A field that combines AI with engineering to create machines capable of performing tasks autonomously.
S
Sentiment analysis: Also known as opinion mining, sentiment analysis is the process of using AI to analyze the tone and opinion of a given text.
Structured data: Structured data is data that is defined and searchable. This includes data like phone numbers, dates, and product SKUs.
Supervised Learning: A type of machine learning where the model is trained on labeled data.
Swarm Intelligence: A collective behavior exhibited by decentralized systems, often inspired by nature (e.g., ant colonies).
T
Token: A token is a basic unit of text that an LLM uses to understand and generate language. A token may be an entire word or parts of a word.
Transfer Learning: A technique where a pre-trained model is adapted for a new, but related, task.
Turing Test: A test proposed by Alan Turing to evaluate a machine's ability to exhibit intelligent behavior indistinguishable from a human.
U
Unstructured data: Unstructured data is data that is undefined and difficult to search. This includes audio, photo, and video content. Most of the data in the world is unstructured.
Unsupervised Learning: A type of machine learning where the model is trained on unlabeled data to find patterns or structures.
V
Validation: The process of evaluating a model's performance on a separate dataset to ensure it generalizes well.
Virtual Assistant: An AI-powered software agent that can perform tasks or services based on user input (e.g., Siri, Alexa).
Voice recognition: Voice recognition, also called speech recognition, is a method of human-computer interaction in which computers listen and interpret human dictation (speech) and produce written or spoken outputs. Examples include Apple's Siri and Amazon's Alexa, devices that enable hands-free requests and tasks.
W
Weak AI: AI designed for specific tasks, as opposed to strong AI (AGI), which can perform any intellectual task a human can.
X
XAI (Explainable AI): AI systems designed to provide transparent and understandable explanations for their decisions.
Z
Zero-Shot Learning: A machine learning approach where a model can perform tasks it has never explicitly been trained on.
Links