Glossary Library

Technical GlossaryDeep Learning

Self-Attention

An attention mechanism in which each element in a sequence directly models its relationship with all others.

Self-attention allows each token or element in a sequence to interact directly with all others. This makes it possible to capture long-range dependencies without relying on strictly sequential processing. It is one of the core ideas at the heart of the Transformer revolution. Because of its power for parallel computation and context modeling, it forms the backbone of modern NLP.

You Might Also Like

Explore these concepts to continue your artificial intelligence journey.

Glossary Cover

veri-bilimi-ve-veri-yonetimi

Aggregation Feature

A feature structure that summarizes lower-level records into higher-level signals meaningful for modeling.

Glossary Cover

veri-muhendisligi-ve-ai-altyapisi

Metadata

The body of descriptive, source, usage, and technical information that exists about data.

Glossary Cover

veri-muhendisligi-ve-ai-altyapisi

Metadata Filtering in Vector Search

An approach that narrows vector similarity results using additional fields such as date, source, user, or category.