Max pooling

As explained in Natural Language Processing in Action, Second Edition

Max pooling is a downsampling operation that retains the largest activation within each local region of a feature map.

Max pooling compresses many convolution outputs into one value: the largest activation in the region. In a text CNN, that peak acts as evidence that a learned word pattern appeared somewhere in the sequence. section 7.2.1 section 7.5.2

Think of convolution as a stencil moving across data and producing a numerical response at each position. Max pooling keeps the strongest response, so a pattern can be detected without preserving every location where it appeared. This trades positional detail for a compact signal. section 7.2.1 section 7.2.7

Max pooling is useful because it:

• Aggregates a large tensor into fewer values, reducing the amount of information passed onward. section 7.5.2
• Measures whether a filter found a strong match somewhere in the input rather than preserving every response. section 7.2.1
• Differs from mean pooling, which averages values and may better represent patterns distributed across several locations. section 7.2.1 section 7.5.2

Detecting a phrase pattern

A text CNN applies a learned kernel across an ordered word sequence. If one position produces a particularly strong activation, max pooling selects that value as the sequence-level signal that the kernel's pattern was present. section 7.2.1

Figure 7.1 A real-life stencil

Use the stencil figure to visualize a kernel moving across input and producing position-dependent responses before pooling selects the strongest one. section 7.2.1

How Natural Language Processing in Action, Second Edition covers it

How deep it goes

Explains maximum selection, tensor compression, and mean-pooling contrast, but does not detail 2D window or stride configuration.

Examples

Uses ordered word-pattern detection, a moving-stencil analogy, and wave-and-sandcastle imagery to illustrate strongest-response selection.

What it assumes

Assumes familiarity with convolution, kernels, filter outputs, and tensors while explaining pooling from an intuitive starting point.

What you can do after

Evaluate/understand how CNNs convert many filter responses into a compact signal for detecting patterns.

How it connects

Connects max pooling to convolution, kernels, filter outputs, tensor reduction, mean pooling, average pooling, GPUs, and PyTorch.

liveBookmanning.com

Read Natural Language Processing in Action, Second Edition 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
  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
  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 Natural Language Processing in Action, Second Edition. The section links point to the parts of the book it draws on.