Glossary category
Foundations
The basic ideas needed to reason clearly about modern AI systems and their limits.
What belongs here
Core concepts that recur across models, agents, evaluation, and software production.
What belongs elsewhere
Implementation-specific training methods, deployment techniques, and vendor products.
Adjacent categories
Start with
Factory areas
Definitions in this category
stable
AI model
The computational component of an AI system that uses learned parameters, encoded knowledge, or both to infer outputs from inputs.
AI system
The operational arrangement that uses one or more AI models with data, software, infrastructure, interfaces, controls, and people to produce and act on outputs.
Algorithm
A specified procedure that transforms inputs into outputs or solves a defined class of problems through a finite set of steps and stated stopping behavior.
Artificial intelligence (AI)
The field concerned with machine-based systems that infer how to produce predictions, content, recommendations, decisions, or actions in pursuit of stated or implicit objectives.
Attention
A learned mechanism that scores relationships among elements and uses those scores to combine information into a new representation.
Classification
Assigning one or more discrete categories to an input, often by converting model scores or probabilities into labels through a decision rule.
Clustering
Grouping examples without predefined class labels according to a chosen representation, similarity measure, and clustering objective.
Computer vision
The field of building computational systems that derive measurements, representations, predictions, or actions from images, video, and other visual signals.
Context window
The token capacity a model can process within one inference request, shared among the input context and, for many systems, the tokens generated in response.
Dataset
An assembled collection of examples or records, with an intended structure and use, for training, tuning, evaluating, or operating an AI system.
Deep learning
Machine learning based on neural networks with many successive layers that learn increasingly useful representations from data.
Embedding
A numeric vector produced by a representation model so useful relationships among items can be compared with geometric operations.
Expert system
A bounded AI system that applies an explicit knowledge base and inference procedure to reproduce part of a specialist's decision process.
Feature
An input variable or derived representation that a machine-learning model actually uses to produce a prediction.
Foundation model
A model trained on broad data, generally through self-supervision at scale, that can be adapted to a wide range of downstream tasks.
Generative AI
AI whose central capability is producing new text, code, images, audio, video, or structured data from a learned generative model.
Inference
Executing a trained or otherwise specified model on input to produce scores, predictions, decisions, or generated content.
Label
A target or reference value attached to an example for supervised learning, evaluation, or later analysis.
Large language model (LLM)
A high-capacity learned model trained on large token sequences to estimate or generate language, often with related capabilities in code and other modalities.
Machine learning (ML)
A family of methods that adjusts a model from data or experience so its performance improves against a defined objective.
Model vocabulary
The finite mapping between token types and identifiers that a tokenizer uses and a model's embedding and output layers are trained to interpret.
Multimodal model
A model that learns or applies relationships across more than one modality, such as text, images, audio, video, sensor signals, or structured data.
Narrow AI
An AI system designed, authorized, or validated for a bounded task and operating domain rather than broad transferable competence.
Natural language processing (NLP)
The field of building computational systems that analyze, retrieve, translate, or generate human language in text or speech.
Neural network
A computational model of connected units whose learned parameters transform inputs into predictions, representations, or generated outputs.
Parameter
A learned numerical value that helps determine how a trained model transforms inputs into outputs.
Probability distribution
A rule that assigns probability to possible outcomes or ranges of outcomes, with total probability equal to one.
Query-key-value attention (QKV)
An attention formulation that compares queries with keys, normalizes the scores into weights, and applies those weights to corresponding values.
Regression
Estimating a numeric response or the relationship between a response and one or more inputs.
Reinforcement learning (RL)
A family of methods in which an agent learns a policy by interacting with an environment and optimizing expected cumulative reward.
Self-supervised learning
Learning in which supervisory targets are generated from the structure of otherwise unlabeled data, such as predicting hidden or next tokens.
Supervised learning
Machine learning from labeled examples that pair inputs with desired outputs.
Synthetic data
Artificially generated records designed to reproduce selected properties of real or imagined data for training, testing, simulation, or controlled sharing.
Token
One vocabulary unit produced or consumed by a model, such as a word, subword, byte sequence, punctuation mark, special marker, or non-text unit.
Tokenization tax
The extra token count, cost, latency, or lost context capacity imposed when a tokenizer represents equivalent content less efficiently in one language, script, domain, or notation than another.
Tokenizer
An algorithm, vocabulary, and set of text-processing rules that encode input into token identifiers and decode identifiers back into usable output.
Training
The process of adjusting a model's parameters to reduce a defined objective on training data, with the aim of producing useful behavior on new inputs.
Transformer
A neural-network architecture that combines self-attention, position information, and feed-forward transformations to model relationships within sequences or other structured inputs.
Turing Test
An imitation game in which a human judge uses text conversation to assess whether a machine can be distinguished from a human participant.
Unsupervised learning
Learning patterns, structure, or representations from data without supplied target labels.