Multi-head attention

As explained in Machine Learning Algorithms in Depth

Multihead attention runs multiple attention mechanisms in parallel and combines their output representations.

Multihead attention runs several attention mechanisms in parallel, producing independent output heads that are concatenated and transformed through a dense layer. This gives a transformer multiple ways to interpret the same input. section 11.3

Within transformer models, multihead attention connects to:

• Self-attention, where the model attends to elements within a sequence. section 11.3
• Encoder–decoder attention, where target queries attend to source keys and values during translation. section 11.3
• Positional encodings, normalization, dense layers, and residual connections surrounding the attention mechanism. section 11.3

Transformer text classification

A transformer classifier uses a Keras MultiHeadAttention layer alongside embeddings, pooling, normalization, dense layers, and training callbacks. section 11.3

Figure 11.11 Multihead attention

Use the multihead-attention figure to inspect how parallel heads are combined. section 11.3

How Machine Learning Algorithms in Depth covers it

How deep it goes

Defines parallel heads, concatenation, and dense transformation, but does not derive attention equations or head computations.

Examples

Illustrates translation attention, transformer architecture, multihead-attention structure, and Keras text classification.

What you can do after

Apply multihead attention through Keras in a transformer text classifier.

How it connects

Connects self-attention with positional encodings, normalization, residual connections, dense layers, and encoder–decoder models.

liveBookmanning.com

Read Machine Learning Algorithms in Depth 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
  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.
• 

  liveBookmanning.com
  The AI Pocket BookA transformer attention mechanism that splits representations into multiple heads to attend to different relationships in parallel.

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 Machine Learning Algorithms in Depth. The section links point to the parts of the book it draws on.