AI Glossary
Simple Definitions for AI Terms
Embeddings
Numerical representations of data (like words or images) that preserve contextual meaning.
Parameters
The internal configuration of an AI model that determines how it learns and makes predictions.
Transformers
A type of neural network architecture that uses self-attention to process sequences — the backbone of modern AI models.
LLM (Large Language Model)
A neural network trained on massive text datasets to understand and generate human language.
Diffusion Models
A generative model that transforms random noise into structured outputs like images or audio over many steps.
Context Window
The maximum number of tokens a model can consider at once when processing or generating content.
Tokens
Small units of text (words or subwords) used as input/output for AI models.