Multi-head attention

As explained in Time Series Forecasting Using Foundation Models

An attention mechanism with multiple parallel attention heads that combines information from different representation subspaces.

Multi-head attention runs several attention mechanisms in parallel, allowing a model to learn different relationships and representations from the same sequence. In time-series forecasting, one head might emphasize trends while another identifies seasonal patterns. The mechanism is described conceptually rather than mathematically. section 1.2.2

Within transformer forecasting architectures, multi-head attention supports several distinct operations:

• Encoder heads relate the current token to other tokens in the known historical sequence, potentially assigning greater weight to nearby time steps. section 1.2.2
• Decoder self-attention is masked so predictions use previous data without accessing future values. section 1.2.3
• A decoder's second attention layer uses the encoder representation, after which projections convert the deep representation into forecast values. section 1.2.3
• Decoder-only forecasting models can stack many layers using multi-head attention; TimesFM also masks input patches during training. section 7.1.1

Figure 1.8 Visualizing the decoder in detail. We see that the output of the encoder is fed to the second attention layer of the decoder; the decoder generates predictions using information learned from the encoder.

Trace how encoder output enters the decoder's second attention layer and contributes to prediction generation. section 1.2.3

How Time Series Forecasting Using Foundation Models covers it

How deep it goes

Explains roles, masking, and architecture connections, but defers the mechanism's mathematical details.

Examples

Illustrates trend and seasonal heads, nearer historical tokens, masked decoder inputs, and TimesFM input patches.

What it assumes

Assumes familiarity with tokens, embeddings, and basic transformer structure while explaining attention roles conceptually.

What you can do after

Evaluate/understand how attention heads, causal masks, and encoder representations support transformer forecasts.

How it connects

Connects self-attention, transformers, encoders, decoders, positional encoding, masking, and time-series forecasting.

liveBookmanning.com

Read Time Series Forecasting Using Foundation Models 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
  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.
• 

  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 Time Series Forecasting Using Foundation Models. The section links point to the parts of the book it draws on.