Max pooling

As explained in Machine Learning Algorithms in Depth

Max pooling is a downsampling operation that retains the largest value within each local window of a feature sequence.

Max pooling is a downsampling operation that retains the largest value within each local window of a feature sequence or feature map. Pooling aggregates information while reducing spatial or temporal dimensions. section 10.2

In a convolutional network, max pooling commonly follows convolution and ReLU activation. Repeated blocks learn increasingly rich features while max pooling reduces feature-map dimensions before later processing. section 10.2.1 section 10.6

The operation appears in several processing settings:

• Use 2D max pooling to reduce image feature maps in a LeNet-style MNIST classifier. section 10.2.1
• Use 1D max pooling after convolutions to process encoded question sequences in a multi-input similarity model. section 10.3.2
• Distinguish maximum aggregation from average pooling and global average pooling, which use different reduction rules. section 10.2

LeNet-style MNIST classifier

A Keras/TensorFlow CNN stacks convolutional, ReLU, and max-pooling operations, then flattens the resulting feature map and applies a dense softmax classifier. section 10.2.1

Figure 10.4 LeNet architecture for MNIST digits classification

Use the LeNet architecture diagram to trace how max pooling reduces feature-map dimensions between convolutional stages. section 10.2.1

How Machine Learning Algorithms in Depth covers it

How deep it goes

Defines maximum aggregation and its architectural role, but does not derive window geometry or pooling gradients.

Examples

Uses LeNet for MNIST image classification and a multi-input Quora question-similarity model with 1D convolutions.

What it assumes

Assumes convolutional layers, feature maps, ReLU activation, and basic CNN classification pipelines.

What you can do after

Apply max pooling via Keras/TensorFlow within image and sequence convolutional architectures.

How it connects

Connects convolutional layers, ReLU activation, feature maps, average pooling, global average pooling, and CNN classifiers.

liveBookmanning.com

Read Machine Learning Algorithms in Depth on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Math and Architectures of Deep Learning
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionA max-pooling layer down-samples local regions by retaining their maximum values.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA two-dimensional pooling layer that downsamples feature maps by taking local maxima.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second Edition
• 

  liveBookmanning.com
  Build a Text-to-Image Generator (from Scratch)Max pooling is a spatial downsampling operation that retains the maximum activation within each local window.
• 

  liveBookmanning.com
  Graph Neural Networks in Actionmax_pool is a PyTorch Geometric pooling function that coarsens a graph by pooling clustered nodes using maximum-valued features.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionMax pooling is a downsampling operation that retains the largest activation within each local region of a feature map.
• 

  liveBookmanning.com
  Evolutionary Deep Learning: Genetic algorithms and neural networksMax pooling is a neural-network operation that downsamples local activation regions by retaining their maximum values.
• 

  liveBookmanning.com
  Sutskever's ListA downsampling operation that retains the largest activation within each local spatial window.

Compare how 10 books explain max pooling →

Related concepts

• downsamplingkind of · Downsampling is the reduction of data quantity, spatial resolution, temporal resolution, or sampling rate by retaining, selecting, or aggregating fewer representative values or observations.
• poolingkind of · Pooling is an operation that aggregates values or representations across regions or axes to produce a reduced or summarized representation.
• convolutional neural networkpart of · A convolutional neural network is a neural-network architecture that applies learned convolutional operations to extract patterns from structured data.
• strided convolutioncontrasts with · A strided convolution is a convolution whose filter moves across input positions by more than one step, typically reducing spatial or temporal resolution.
• convolutional layeruses · A convolutional layer is a neural-network layer that applies shared learned filters to local regions of structured input to produce feature representations.
• neural network layerkind of · A neural network layer is a computational stage or component that transforms input representations into outputs within a neural network.

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.