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
A computational component whose learned or encoded structure transforms inputs into outputs such as scores, predictions, classifications, or generated content.
AI system
The complete operational arrangement that uses one or more AI models together with data, software, infrastructure, interfaces, controls, and people.
Algorithm
A finite set of rules or procedures for transforming inputs into outputs or solving a class of problems.
Artificial intelligence (AI)
The field and class of machine-based systems that produce predictions, recommendations, decisions, or generated content in pursuit of human-defined objectives.
Attention
A mechanism that computes how strongly elements in a representation should influence one another when producing a new representation.
Classification
Predicting which discrete category or categories apply to an input.
Clustering
Grouping examples by similarity without requiring predefined class labels.
Computer vision
The field of building computational systems that extract representations, predictions, or actions from images, video, and other visual data.
Dataset
A deliberately assembled collection of examples or records used to train, tune, evaluate, or operate an AI system.
Deep learning
Machine learning based on neural networks with multiple representational layers, allowing complex features to be learned from data.
Embedding
A learned numeric vector that represents an item so that useful semantic or structural relationships can be measured geometrically.
Expert system
A system that applies an explicitly represented knowledge base and inference rules to make recommendations or decisions within a bounded domain.
Feature
A measurable input attribute or derived representation used by a machine-learning system.
Foundation model
A broadly trained model, usually learned through self-supervision on diverse data, that can be adapted to many downstream tasks.
Generative AI
AI designed to produce new content, such as text, code, images, audio, video, or structured data, based on patterns learned from data.
Inference
Running a trained model on input to produce an output.
Label
The known target value attached to an example for supervised learning or evaluation.
Large language model (LLM)
A large learned model trained to process and generate sequences of language tokens, often with capabilities that extend to code, tools, and multiple modalities.
Machine learning (ML)
A family of methods in which computational models improve task performance by finding patterns in data rather than relying only on explicitly programmed rules.
Model vocabulary
The finite set of token identifiers a tokenizer and model can represent directly.
Multimodal model
A model that accepts, relates, or generates more than one modality, such as text, images, audio, video, or structured data.
Narrow AI
An AI system designed or validated for a bounded task or domain rather than general competence.
Natural language processing (NLP)
The field of building computational systems that analyze, represent, understand, retrieve, translate, or generate human language.
Neural network
A parameterized computational model composed of connected layers that transform representations and learn by adjusting weights to reduce an objective.
Parameter
A value learned during training that helps determine how a model transforms inputs into outputs.
Probability distribution
A set of possible outcomes paired with nonnegative probabilities that sum to one.
Query-key-value attention (QKV)
The attention formulation in which queries are matched against keys to calculate weights applied to corresponding values.
Regression
Predicting a continuous numeric value from input data.
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 intended to reproduce useful properties of real data for training, testing, simulation, or privacy.
Token
A unit into which model input or output is segmented for processing; a token may be a whole word, part of a word, punctuation, or another symbol.
Tokenizer
Software that converts text or other input into model tokens and converts generated token identifiers back into human-usable form.
Training
The process of adjusting a model's parameters using data and an optimization objective so that its behavior improves on a target task or distribution.
Transformer
A neural-network architecture built around attention mechanisms that process relationships among sequence elements in parallel.
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.
working
Context window
The maximum token span a model can directly consider in one inference request, including instructions, conversation, retrieved material, tool schemas, and expected output.
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.