Multi-head attention

As explained in The AI Pocket Book

A transformer attention mechanism that splits representations into multiple heads to attend to different relationships in parallel.

Multi-head attention splits an attention mechanism into separate heads. Each head analyzes a different chunk of an embedding vector, so the model can specialize in several kinds of relationships at once. section 1.20

Specialized segments

Imagine one segment of an embedding vector handling animal-related information while another handles tree-related information. The vectors remain difficult to interpret, but separating the work into heads performs better in practice than using one head for the whole vector. section 1.20

Figure 1.10 The attention mechanism calculates the relative relevance of all tokens in the context window to contextualize or disambiguate the last token.

Use the attention figure to connect multiple heads with the broader task of comparing token relevance while contextualizing or disambiguating the last token. section 1.20

How The AI Pocket Book covers it

How deep it goes

Defines separate vector chunks and explains their specialization, but stops short of detailing attention calculations or head outputs.

Examples

Illustrates specialization with hypothetical animal-related and tree-related embedding segments.

What it assumes

Assumes attention and embedding vectors, while relating them to contextualization and transformer layers.

What you can do after

Evaluate how separate attention heads can specialize representations and outperform a single whole-vector attention head.

How it connects

Connects attention with embedding vectors, contextualization, transformer layers, and language models.

liveBookmanning.com

Read The AI Pocket Book on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionMulti-head attention computes multiple attention representations in parallel and combines them, potentially using distinct query and source sequences.
• 

  liveBookmanning.com
  Build a Text-to-Image Generator (from Scratch)An attention mechanism that computes attention through multiple separate query, key, and value subspaces to capture different relationships simultaneously.
• 

  liveBookmanning.com
  Transformers in ActionMultihead attention is an attention mechanism that computes multiple attention patterns in parallel so a model can represent different relationships among sequence positions.
• 

  liveBookmanning.com
  Learn Generative AI with PyTorchA self-attention variant that splits representations into multiple attention heads to capture different relationships in parallel.
• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsAn attention mechanism that uses multiple attention heads to attend to different contexts or aspects of the input in parallel.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionAn attention variant that runs several attention computations in parallel with different parameters to learn different relationships.
• 

  liveBookmanning.com
  Graph Neural Networks in ActionAn attention technique that computes multiple attention operations in parallel and combines their outputs.
• 

  liveBookmanning.com
  Build a Large Language Model (From Scratch)An attention technique that computes several independent attention heads in parallel and combines their outputs to capture different relationships in the same sequence.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionMultiHeadAttention is a Keras layer that computes attention through multiple parallel attention heads and combines their outputs.
• 

  liveBookmanning.com
  Time Series Forecasting Using Foundation ModelsAn attention mechanism with multiple parallel attention heads that combines information from different representation subspaces.
• 

  liveBookmanning.com
  Machine Learning Algorithms in DepthMultihead attention runs multiple attention mechanisms in parallel and combines their output representations.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionAn attention mechanism that runs several attention heads in parallel, each learning different projections and relationships.
• 

  liveBookmanning.com
  Optimization Algorithms: AI techniques for design, planning, and control problemsMulti-head self-attention computes several attention operations in parallel so a sequence representation can capture different relationships among its elements.

Compare how 14 books explain multi-head attention →

Related concepts

• graph attention networkused by · A graph attention network is a graph neural network that uses attention weights to aggregate information from neighboring nodes, allowing their contributions to differ.
• grouped-query attentionequivalent to · Grouped-query attention partitions query heads into groups whose members share key and value projections, reducing attention computation and memory use.
• attentionkind of · Attention is a neural-network mechanism that computes input-dependent weights to combine information according to its relevance to a computation.
• attention headhas part · An attention head is an independently parameterized attention computation that evaluates relationships among input elements and combines information from them into a contextualized representation.
• transformer architectureused by · A transformer architecture is a neural-network architecture that processes sequences or other structured inputs using attention mechanisms and related transformations.
• encoderpart of · An encoder is a component that transforms input data into an encoded representation for subsequent processing, reconstruction, comparison, or transmission.

This explainer was generated by Manning's knowledge graph from the text of The AI Pocket Book. The section links point to the parts of the book it draws on.