Max pooling

As explained in Evolutionary Deep Learning: Genetic algorithms and neural networks

Max pooling is a neural-network operation that downsamples local activation regions by retaining their maximum values.

Max pooling downsamples local activation regions by retaining their largest values. In a convolutional neural network, it summarizes feature maps after convolution, reducing noisy and oversized outputs before later layers process them. section 7.1

A practical Keras configuration uses pooling to progressively shrink spatial dimensions:

• Apply MaxPooling2D((2, 2)) after convolutional layers. section 7.1
• Use padding="same" when preserving compatible boundary behavior matters. section 7.1
• Inspect model.summary() to verify the resulting feature-map shapes and parameter counts. section 7.1

Progressive spatial reduction

A CNN can move from 28×28×64 after its first convolution to 14×14×64 after max pooling, then to 7×7×32 and 2×2×16 through successive pooling layers. In an autoencoder, MaxPool layers are added to the encoder to create the funnel or reduction architecture, while UpSampling layers mirror that reduction in the decoder. section 7.1 section 8.2.1

Figure 7.4 Max pooling operation

Shows how maximum pooling reduces the output produced by a convolutional operation. section 7.1

How Evolutionary Deep Learning: Genetic algorithms and neural networks covers it

How deep it goes

Explains the reduction purpose and Keras placement, then stops short of deriving pooling mathematically or examining its learned behavior.

Examples

Uses Fashion-MNIST CNN layers, model summaries, a max-pooling figure, and automatically generated autoencoder gene sequences.

What it assumes

Assumes familiarity with convolutional layers and teaches pooling through their role in reducing convolution outputs.

What you can do after

Operate/configure Keras MaxPooling2D layers and inspect their effect on convolutional model dimensions.

How it connects

Connects max pooling to convolutional neural networks, convolution, feature maps, autoencoders, encoders, decoders, and upsampling.

liveBookmanning.com

Read Evolutionary Deep Learning: Genetic algorithms and neural networks 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
  Machine Learning Algorithms in DepthMax pooling is a downsampling operation that retains the largest value within each local window of a feature sequence.
• 

  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 Evolutionary Deep Learning: Genetic algorithms and neural networks. The section links point to the parts of the book it draws on.