Concept graph
Generative AI and LLM glossary
Clear AI definitions with practical context, examples, and links to related models, tools, and concepts.
Machine learning
Graph Machine Learning
Graph machine learning applies statistical and neural methods to data represented as nodes, edges, and attributes so models can learn from relationships as well as individual records.
Machine Learning
graph-attention-network
A neural network architecture that employs attention mechanisms to process graph-structured data.
Neural Networks
graph-convolutional-network
A type of neural network designed to process data structured as graphs.
Database Technology
graph-database
A database specifically designed to store and navigate relationships between data points using graph structures.
machine-learning
graph-embedding
A technique for transforming graph-structured data into a continuous vector space while preserving its properties.
Deep Learning
graph-neural-network
A neural network designed to work directly with graph-structured data.
Mathematics
graph-theory
A field of mathematics focused on the study of graphs as mathematical structures.
Statistics
graphical-models
Statistical models that represent variables and their conditional dependencies using a graph.
Model Training
grid-search
A method for hyperparameter optimization that exhaustively searches through a specified subset of hyperparameters.
Retrieval
Grounding
Grounding means tying model claims to retrieved documents, tools, or other checkable evidence instead of parametric memory alone.
Safety
Hallucination
Hallucination is fluent model output that is not supported by the provided context or by checkable facts.
Computer Science
human-computer-interaction-hci
The study and design of how people interact with computers and other technologies.
Machine Learning
Hyperparameter tuning
Hyperparameter tuning searches training or decoding settings that are not learned as weights, such as learning rate or temperature.
computer-vision
image-segmentation
The process of partitioning an image into multiple segments to simplify analysis.
Machine Learning
incremental-learning
A machine learning approach that updates models continuously with new data without retraining from scratch.
Models
Indic LLM
An Indic LLM is a language model optimized for Indian languages, scripts, romanized text, code-mixing, and India-specific cultural or domain context.
Agent security
Indirect prompt injection
Indirect prompt injection happens when untrusted external content, such as a webpage, email, document, or tool result, contains instructions that try to steer an AI system.
Serving
Inference
Inference is running a trained model on new input to produce an output. Training updates the model's weights. Inference does not.
Data Management
information-retrieval
The process of obtaining information system resources that are relevant to an information need.
Networking
internet-of-things-iot
A network of interconnected devices that communicate and exchange data over the internet.
Product
JSON mode
JSON mode asks a model to emit syntactically valid JSON, without necessarily matching a specific schema.
Unsupervised Learning
k-means-clustering
An unsupervised learning algorithm used for partitioning data into clusters.
Machine Learning
K-Nearest Neighbors (KNN)
A simple algorithm that classifies data points based on the classes of their nearest neighbors.
Model Optimization
Knowledge Distillation
A process of transferring knowledge from a large model to a smaller model.