AI Glossary

Multi-Head Attention

Coverage in development

Transformer block running several attention heads in parallel to capture diverse relationships.

Definition

Transformer block running several attention heads in parallel to capture diverse relationships.

Plain English explanation

Multi-head attention looks in multiple ways at once.

Last reviewed

Sources

Correction request

If a technology assignment or hub description is inaccurate, submit a correction via the Corrections Policy.

All technologies → · AI Models → · APIs & SDKs → · Integrations → · Compliance → · Browse all companies → · Explore industries → · Compare →