Concept graph
Generative AI and LLM glossary
Clear AI definitions with practical context, examples, and links to related models, tools, and concepts.
Retrieval
Embedding
An embedding is a dense vector that represents text, code, or media so similar items land near each other for search and clustering.
Probabilistic Models
energy-based-model
A probabilistic model that associates a scalar energy value with each configuration of variables to model distributions.
Learning Techniques
Ensemble learning
Ensemble learning combines several models so the group prediction is more stable than any single model.
AI Safety and Governance
Explainability
Explainability describes how clearly people can understand why an AI system produced a particular output or decision.
robotics
explainable-robotics
A field of study focused on making robotic systems understandable and transparent to users.
Data Analysis
exploratory-data-analysis
An approach to analyzing data sets to summarize their main characteristics.
Evaluation
Faithfulness
Faithfulness is whether every claim in a generated answer is supported by the supplied evidence.
Data Preparation
Feature Engineering
The process of selecting, modifying, or creating features from raw data.
Model Interpretation
Feature Importance
A measure of how much a feature contributes to the predictive power of a model.
Machine Learning
Feature Mapping
The process of transforming input features into a more suitable format for modeling.
Data Preprocessing
Feature Scaling
The process of standardizing or normalizing features so they contribute equally to the model.
Machine Learning
Feature Vector
A numerical representation of an object's characteristics used in machine learning.
Data Processing
feature-extraction
The process of transforming raw data into a set of usable characteristics for model training.
Data Processing
feature-selection
The process of selecting a subset of relevant features for model training.
Machine Learning
Federated Learning
A machine learning approach that allows models to be trained across decentralized devices or servers holding local data samples.
Machine Learning
few-shot-learning
A machine learning paradigm that trains models with very few labeled examples.
Training
Fine-tuning
Fine-tuning continues training a pretrained model on a smaller, task-specific dataset so it follows that task more reliably.
Agents
Function calling
Function calling is the API pattern where a model returns a named function and arguments for the application to execute.
Neural Networks
Generative Adversarial Network (GAN)
A generative adversarial network (GAN) trains a generator and a discriminator in opposition so the generator learns to produce samples that resemble a training distribution.
Artificial Intelligence
Generative AI
AI systems that can create new content, such as text, images, or music.
Modeling
Generative Model
A generative model learns a data distribution so it can create new samples such as text, images, audio, code, or structured records.
Evaluation
Golden set
A golden set is a versioned collection of labeled tasks used to score models and prompts against the behavior you actually want.
Machine Learning
Gradient Boosting
A machine learning technique that builds models in a sequential manner.
Optimization
Gradient Descent
An optimization algorithm used to minimize the loss function in machine learning.