Transformer architecture

As explained in Inside Deep Learning: Math, Algorithms, Models

A sequence model built from positional encoding and multiheaded attention, used here as the standard original design for NLP and other tasks.

A transformer replaces recurrent sequence processing with positional encoding and multiheaded attention. This enables parallel processing and scales better with depth and powerful compute, although training is computationally expensive. section 12.0 section 12.5

A vanilla transformer is organized around two block types:

• Encoder blocks apply self-attention, using the same sequence as queries, keys, and values, followed by a residual linear layer. They can stand alone for tasks such as sentiment classification. section 12.5.2
• Decoder blocks usually pair with an encoder for multi-output tasks such as machine translation. Their additional attention layer uses encoder outputs as keys and values. section 12.5.2
• Positional encodings supply sequence information because transformer blocks have no explicit recurrent time connections. section 12.5.2
• Autoregressive models require a triangular mask to prevent attention from accessing future inputs. section 12.5.2

PyTorch classifier skeleton

A practical encoder classifier embeds tokens, adds positional encodings, stacks three TransformerEncoder layers with eight attention heads, pools attention outputs, and predicts classes through linear layers. section 12.5.2

Figure 12.7 The two types of transformer blocks: the encoder (left) and decoder (right). Both use layer normalization, residual connections, and MHA layers. The first MHA in each is called self-attention because the same input is used for Q, K, and V.

Use the architecture diagram to compare encoder and decoder paths, residual connections, layer normalization, self-attention, and multiheaded attention. section 12.5.2

How Inside Deep Learning: Math, Algorithms, Models covers it

How deep it goes

Defines positional encoding, multiheaded attention, encoder-decoder blocks, residual paths, and future masking, without deriving their mathematics.

Examples

Uses sentiment classification, machine translation, PyTorch encoder code, and training-accuracy comparisons with GRU, CNN, and attention models.

What it assumes

Assumes familiarity with sequence modeling and develops positional encoding and multiheaded attention before assembling transformer blocks.

What you can do after

Build a basic PyTorch transformer classifier and recognize when autoregressive attention requires future-token masking.

How it connects

Connects positional encoding, multiheaded attention, self-attention, residual connections, layer normalization, RNNs, and sequence-to-sequence models.

liveBookmanning.com

Read Inside Deep Learning: Math, Algorithms, Models on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Learn Generative AI with PyTorchThe internal design and structural organization of a Transformer model built around decoder blocks or self-attention components.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionA transformer is a neural network architecture that uses attention mechanisms to process sequences and model relationships among their elements.
• 

  liveBookmanning.com
  Sutskever's ListA Transformer is a neural network architecture based primarily on attention mechanisms for modeling relationships among sequence elements.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA neural-network architecture based on attention mechanisms, used here as the core architecture for large language models.
• 

  liveBookmanning.com
  Build a Text-to-Image Generator (from Scratch)A transformer architecture is a neural-network architecture that uses attention mechanisms to process relationships among elements in a sequence or other structured input.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionA Transformer is a neural-network architecture designed to process sets or sequences using attention-based contextual representations.
• 

  liveBookmanning.com
  How Large Language Models WorkA transformer is a neural-network architecture that uses attention mechanisms to process relationships among elements in a sequence.
• 

  liveBookmanning.com
  AI-Powered SearchA transformer is a neural-network architecture that models relationships among sequence elements using attention and can encode and decode representations.
• 

  liveBookmanning.com
  Transformers in ActionA transformer is a neural network architecture that processes sequential and other structured data using attention mechanisms.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionA neural network architecture for sequence modeling and content understanding based on attention rather than recurrence or convolution.
• 

  liveBookmanning.com
  LLMs in ProductionA transformer architecture is a neural-network architecture that models sequence relationships primarily through attention rather than recurrence or convolution.
• 

  liveBookmanning.com
  Grokking AI ApplicationsA transformer is a neural-network architecture for sequential data that uses attention to relate elements of an input sequence.
• 

  liveBookmanning.com
  The AI Pocket BookA neural network architecture that contextualizes each token using surrounding tokens rather than compressing the whole prompt into one summary vector.
• 

  liveBookmanning.com
  Time Series Forecasting Using Foundation ModelsA neural-network architecture built from stacked attention and feed-forward processing components, typically organized into encoder and decoder parts.
• 

  liveBookmanning.com
  Machine Learning Algorithms in DepthA transformer model is a neural network architecture that uses attention-based mechanisms to model contextual relationships in structured sequences or other data.
• 

  liveBookmanning.com
  Grokking AI Algorithms, Second EditionThe Transformer is a neural-network architecture based primarily on attention mechanisms for processing sequences and modeling context.
• 

  liveBookmanning.com
  Hugging Face in ActionThe Transformer architecture is a neural-network architecture based on attention mechanisms for processing sequences and other structured inputs.
• 

  liveBookmanning.com
  Domain-Specific Small Language ModelsA neural network architecture for sequence modeling built around self-attention and parallel processing, underlying both large and small language models.
• 

  liveBookmanning.com
  Introduction to Generative AI, Second EditionA transformer is a neural-network architecture for sequence modeling that uses attention, especially self-attention, rather than recurrence.
• 

  liveBookmanning.com
  Build AI-Enhanced Web AppsA transformer model is a neural-network architecture that uses attention mechanisms to model contextual relationships in sequence data.
• 

  liveBookmanning.com
  Build a Large Language Model (From Scratch)a neural network architecture based on self-attention mechanisms that enables processing of sequential data and underpins many large language models.
• 

  liveBookmanning.com
  Build a Website with ChatGPTA transformer is a neural-network architecture that processes sequences using attention mechanisms to model relationships among their components.
• 

  liveBookmanning.com
  Data Analysis with LLMsThe Transformer is a neural-network architecture designed to model relationships in sequences, especially sequences with variable-length inputs or outputs.
• 

  liveBookmanning.com
  Generative AI in ActionThe Transformer architecture is a neural-network architecture based primarily on attention mechanisms for processing sequences.
• 

  liveBookmanning.com
  Coding with AIA Transformer is a neural-network architecture that processes sequence elements using attention and can process them in parallel.
• 

  liveBookmanning.com
  Optimization Algorithms: AI techniques for design, planning, and control problemsA transformer architecture is a neural-network architecture that processes sequences primarily through attention mechanisms rather than recurrence.
• 

  liveBookmanning.com
  Essential GraphRAGA transformer architecture is a neural-network architecture that processes sequences using attention-based representations and supports efficient language modeling.

Compare how 28 books explain transformer architecture →

Related concepts

• attentionuses · Attention is a neural-network mechanism that computes input-dependent weights to combine information according to its relevance to a computation.
• encoderhas part · An encoder is a component that transforms input data into an encoded representation for subsequent processing, reconstruction, comparison, or transmission.
• decodehas part · Decoding is the process of transforming an encoded or internal representation into an interpretable or target-form output.
• Vision Transformerincludes · A Vision Transformer is a Transformer-based neural-network architecture that processes images as sequences of tokenized regions using attention.
• model architecturekind of · The structural organization of a computational system’s components, relationships, and operations that determines how it processes information or behaves.
• GPT-2includes · GPT-2 is a family of autoregressive, decoder-only Transformer language models developed by OpenAI that generate text by predicting successive tokens from preceding context.

This explainer was generated by Manning's knowledge graph from the text of Inside Deep Learning: Math, Algorithms, Models. The section links point to the parts of the book it draws on.