Welcome to the AI Glossary — your essential reference for understanding key terms in artificial intelligence.
Core Concepts
Embeddings
Vector representations of words, phrases, or other data used to capture meaning or similarity.
Parameters
The internal variables of a model learned during training that determine its behavior.
Transformers
A neural network architecture that uses self-attention for sequence modeling. Foundation for GPT, BERT, etc.
LLM (Large Language Model)
A type of AI model trained on vast amounts of text to understand and generate human language.
Diffusion Models
Image generation models that learn by reversing a gradual noising process. Used by tools like DALL·E and Midjourney.
Context Window
The amount of text a model can “see” at once. Larger windows allow for longer input understanding.
Tokens
Chunks of text (words, subwords, or characters) used as units of processing by language models.