Caesar AI Atlas

Multi-head Self-attention

Also known as: Multi head Self attention Β· Multi-head Self Attention

Caesar AI Atlas Definition

Multi-head self-attention is an attention mechanism that computes several attention patterns in parallel over the same input sequence. Each head can capture different relationships among tokens, and the combined output helps transformer models represent complex contextual dependencies.

Other Definitions

Multi-head Self-attention Source

An extension of self-attention that applies the self-attention mechanism multiple times for each position in the input sequence. Transformers introduced multi-head self-attention.

Related Terms