GenAIWiki

Concept graph

Generative AI and LLM glossary

Clear AI definitions with practical context, examples, and links to related models, tools, and concepts.

Natural Language Processing

Natural Language Understanding

A subfield of natural language processing focusing on machine comprehension of human language.

Natural Language Processing

natural-language-generation

The use of algorithms to produce human-like text based on given data or prompts.

natural-language-processing

natural-language-generation-nlg

The automatic process of generating coherent and contextually relevant natural language text from structured data.

Artificial Intelligence

natural-language-processing

A branch of artificial intelligence that focuses on the interaction between computers and human language.

Deep Learning

Neural Architecture Search

An automated process for designing neural network architectures optimized for specific tasks.

Machine Learning

Neural Network

A computational model inspired by the way biological neural networks in the human brain work.

hybrid AI

neural-symbolic-integration

A hybrid approach that combines neural networks with symbolic reasoning.

Biotechnology

Neurotechnology

Technologies designed to understand, interface with, or manipulate the nervous system.

information-theory

noisy-channel-coding

A method for encoding data to protect against errors during transmission over noisy channels.

data-quality

noisy-labels

Labels in a dataset that are inaccurate or wrong, often leading to misguidance in model training.

machine learning

one-shot-learning

A machine learning approach that enables a model to learn information about object categories from a single training example.

Knowledge Representation

ontologies

Formal representations of a set of concepts within a domain and the relationships between those concepts.

Knowledge Representation

ontology

An ontology is a formal representation of a set of concepts within a domain.

Models and Deployment

Open Weights

Open weights are downloadable model parameters that teams can inspect, run, fine-tune, or redistribute only to the extent permitted by the model's license.

Security

OpenAI Daybreak

OpenAI Daybreak is a vetted access program that gives authorized cybersecurity defenders controlled use of frontier models—and, in Daybreak Red, purpose-trained cyber models such as GPT-5.6-Cyber.

machine learning

out-of-distribution-generalization

The ability of a model to perform well on unseen data that is different from the training set.

data-analysis

outlier

An observation point that is distant from other observations in the dataset.

Data Analysis

Outlier Detection

The identification of data points that deviate significantly from the majority of data.

Modeling

Overfitting

A modeling error that occurs when a model learns noise and details from the training data.

data-preprocessing

pipeline

A sequence of data processing steps for machine learning workflows.

evaluation

precision-recall-curve

A graphical representation of a model's trade-off between precision and recall.

Data Analysis

predictive-analytics

The use of statistical techniques to forecast future events based on historical data.

Data Science

Principal Component Analysis (PCA)

A dimensionality reduction technique used to simplify datasets while preserving variance.

data-analysis

principal-component-analysis

A dimensionality reduction technique that transforms data into a set of orthogonal components.