AI Glossary: 3,885 terms, defined

Plain-language definitions of the vocabulary used across machine learning, model architectures, tooling and AI safety. Every entry opens with a one-sentence definition, then explains where the term is used.

66 terms

Computer Vision

Object Detection

Object detection is a computer vision technique that identifies and locates multiple objects within an image or video by drawing bounding boxes and assigning labels.

Other

Object Identification

Object Identification is the process of detecting and recognizing specific items within images or videos using computer vision techniques.

Computer Vision

Object Recognition

Object Recognition is a computer vision technology that identifies and classifies objects within an image or video.

AI Agents & Systems

Obligations

Obligations are duties or commitments that require an individual or organization to perform or refrain from certain actions.

MLOps & Infrastructure

Observability

Observability is the ability to measure a system’s internal state by analyzing its outputs, enabling insight into complex software or infrastructure behavior.

Machine Learning

Occam’s Razor

Occam's Razor is a problem-solving principle that suggests the simplest explanation is often the correct one.

Deep Learning & Neural Networks

Occupancy Network

An occupancy network is a 3D representation technique used in fields like robotics and computer vision to determine the presence or absence of objects within a specified space.

Other

OCR

OCR is Optical Character Recognition, a technology that converts images of text into editable and searchable digital text.

Other

OCR (Optical Character Recognition)

OCR (Optical Character Recognition) is a technology that converts different types of documents, such as scanned paper documents or images, into editable and searchable digital text.

AI Agents & Systems

Odometry

Odometry is the process of estimating a robot's or vehicle's position and orientation by measuring its motion over time.

AI Ethics

OECD AI Principles

OECD AI Principles are a set of guidelines designed to promote responsible and trustworthy development and use of artificial intelligence worldwide.

Reinforcement Learning

Off-Policy Learning

Off-Policy Learning is a reinforcement learning method where the agent learns the value of an optimal policy independently from the actions taken by a different behavior policy.

MLOps & Infrastructure

Offline Inference

Offline inference is the process of running machine learning models on pre-collected data without requiring real-time or live input, typically in batch mode.

Machine Learning

Offline Learning

Offline learning is a machine learning approach where models are trained on a pre-existing dataset without continuous updates from new data.

Other

Offline Voice Recognition

Offline voice recognition is the technology that enables speech-to-text processing directly on a device without needing an internet connection.

MLOps & Infrastructure

On-Demand Instances

On-Demand Instances are cloud computing resources that are available for immediate use and billed per hour or second without long-term commitment.

Generative AI

On-Device AI

On-Device AI is artificial intelligence technology that processes data and runs algorithms locally on a device without relying on cloud servers.

Reinforcement Learning

On-Policy Learning

On-Policy Learning is a reinforcement learning approach where the agent learns the value of the policy it is currently following to make decisions.

Other

On-Premise AI

On-Premise AI is artificial intelligence software and hardware deployed and managed within a company’s own physical infrastructure rather than in the cloud.

Machine Learning

One-Hot Encoding

One-Hot Encoding is a method of converting categorical data into a binary matrix representation where each category is represented by a unique binary vector.

Page 1 of 3

About the TiorAI AI Glossary

The TiorAI AI Glossary is a free reference of 3,885 artificial intelligence terms, each defined in plain English. Every entry opens with a one-sentence definition that stands on its own, then explains where the term is actually used and how it sits next to the ideas around it. There is nothing to sign up for and nothing to download: each definition has its own page and its own URL, so a term you needed once can be linked to and found again.

Three ways to find a term

They combine, and none of them cancels the others. The A to Z strip narrows the index to a single initial, with the # key collecting the entries that begin with a digit or a symbol and that no letter would reach. The category filter cuts the glossary to one of sixteen subject areas, among them Machine Learning, Deep Learning and Neural Networks, Natural Language Processing, Computer Vision, Generative AI, Reinforcement Learning, AI Agents and Systems, MLOps and Infrastructure, Data and Analytics, and AI Ethics. The search field matches names and definitions, so a concept you can only half-name still surfaces. Every combination has its own URL, which means a narrowed view can be bookmarked or sent to a colleague.

Read more Read less

What the definitions cover

The vocabulary of modern AI, at the three depths people arrive needing. The fundamentals a first week runs into — model, parameter, training, inference, overfitting. The architecture behind current systems — transformers, attention, embeddings, diffusion, retrieval-augmented generation. And the operational and governance language that turns up in a procurement review or a policy document — fine-tuning, hallucination, alignment, model drift, bias. Terms are defined as they are used in practice rather than as they appear in a paper abstract.

Definitions that answer first

Each entry leads with the answer. The opening sentence says what the term means without assuming the rest of the page, which is what makes an entry useful to someone who arrived from a search with exactly one question. The explanation underneath is for the reader who wants more than that: what the idea is commonly confused with, what it looks like in practice, and which neighbouring terms are worth reading next. The card in the index above shows the opening of that definition, so you can tell from the results whether an entry is the one you want.

Where the glossary fits

A glossary answers what something means; it is not the place that tells you what to do about it. Where a concept has products behind it, the AI tools directory is where they are listed, and where it has a working instruction behind it, the prompt library is where that lives. Entries link out to those when the link earns its place, and the glossary stays what a glossary is — the definitions, ordered so they can be browsed, and written so a single one can be read on its own.

Using this glossary

How is the glossary ordered?

Alphabetically by term name, which is the order a reference work is browsed in and the order every page of this archive has always used. The sort menu can switch it to reverse alphabetical, or to recently added and recently updated if you want to see what has changed.

What does the letter strip do?

It narrows the index to terms whose name begins with that character, and it keeps whatever else you have set — a category filter, a search, a sort — so you can move between letters without starting again. The # entry collects the terms that begin with a digit or a symbol, which no letter would reach.

Why do some terms have no specific category?

Entries that span several areas, or that predate the current category set, sit under “Other”. It holds a large share of the glossary, so the filter is most useful for narrowing to a named topic rather than for excluding one.

What is in a glossary entry?

A short definition in plain language, then a longer explanation of where the term is used and how it relates to neighbouring concepts. The card above shows the opening of that definition; the entry itself also links to related terms and, where relevant, to the AI tools that implement the idea.

How do I search the glossary?

The field at the top matches term names and definitions, so a concept you can only half-name will usually surface. Search combines with the category filter and the letter strip, and every combination has its own URL, so a narrowed view can be bookmarked or shared.