Convolutional neural network

As explained in The AI Pocket Book

A neural network architecture that applies convolutions and downsampling to learn spatial features from grid-like data such as images.

A convolutional neural network (CNN) processes grid-like data, especially images, by repeatedly filtering and shrinking it until useful spatial features support a category prediction. It assumes that recognizing an object depends more on its parts than on their exact positions. section 1.31

A CNN works in a repeated pipeline:

• Treats an image as a table of pixel values. section 1.31
• Applies several convolutions, each using small matrices whose values are learned during training. section 1.31
• Combines the filtered results into a new image, then downsamples it by spatially shrinking neighboring values. section 1.31
• Repeats filtering and downsampling so later stages detect increasingly abstract patterns while discarding precise locations. section 1.31

From pixels to a strawberry

Given an image, a CNN might learn filters that blur regions, highlight a color, or detect sharp changes such as diagonal lines. After successive transformations, those patterns support a prediction such as “strawberry.” A 1024 × 1024 image might first shrink to 512 × 512 by averaging groups of neighboring pixels. section 1.31

Figure 1.11 A diffusion model is trained to improve a corrupted image paired with its caption.

A CNN also appears inside conditional diffusion models, where a U-Net-type CNN learns to repair a corrupted image using a text-caption embedding. section 1.32

How The AI Pocket Book covers it

How deep it goes

Explains learned filters, repeated convolutions, downsampling, and spatial abstraction without deriving the mathematics.

Examples

Uses strawberry classification, cat parts, learned visual filters, pixel downsampling, and diffusion-based image repair.

What it assumes

Assumes basic familiarity with images as pixel grids and machine learning, while defining convolutions and learned filters.

What you can do after

Evaluate/understand how CNNs transform pixels into increasingly abstract features for image classification and multimodal generation.

How it connects

Connects convolutions and downsampling with embeddings, transformers, multimodal AI, and machine learning.

liveBookmanning.com

Read The AI Pocket Book on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionA convolutional neural network is a neural network that applies learned convolutional filters to structured inputs to detect local patterns and construct hierarchical representations.
• 

  liveBookmanning.com
  Sutskever's ListA convolutional neural network is a neural network architecture that applies learned convolutional filters to structured input such as images.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionA convolutional neural network is a neural network that applies convolution-based operations to learn spatial or locally structured features, especially from grid-like data such as images.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA neural network built from convolution and pooling layers that processes data with local spatial structure.
• 

  liveBookmanning.com
  Evolutionary Deep Learning: Genetic algorithms and neural networksA convolutional neural network is a neural network that processes structured inputs with learned convolutional filters, typically for tasks such as image classification.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionA neural network that uses convolutional layers to process spatial data.
• 

  liveBookmanning.com
  Distributed Machine Learning PatternsA convolutional neural network is a neural network model that uses convolutional operations to learn spatial or locally structured representations.
• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsA neural-network design that uses convolutional layers to exploit spatial structure in image data.
• 

  liveBookmanning.com
  Graph Neural Networks in ActionA convolutional neural network is a neural network that applies learned convolutional filters to exploit local spatial structure, especially in grid-like data such as images.
• 

  liveBookmanning.com
  Learn Generative AI with PyTorchA neural network architecture using convolution operations, here applied to multidimensional music data to extract spatial features.
• 

  liveBookmanning.com
  Data Without LabelsA convolutional neural network is a neural-network model that uses convolutional operations to learn spatial or locally structured features.
• 

  liveBookmanning.com
  Math and Architectures of Deep LearningA neural network that uses convolutional layers to process structured grid data such as images.
• 

  liveBookmanning.com
  Grokking Machine LearningA neural-network architecture that uses convolutional operations to learn localized and hierarchical patterns, especially in structured data such as images.
• 

  liveBookmanning.com
  Grokking AI Algorithms, Second EditionA convolutional neural network is a neural-network architecture that applies learned convolutional filters and typically pooling operations to detect spatial patterns in structured data such as images.
• 

  liveBookmanning.com
  Delivering Machine Learning Projects: From design to deploymentA convolutional network is a neural network architecture that applies local filters over structured inputs to capture spatial or local patterns.
• 

  liveBookmanning.com
  Machine Learning Algorithms in DepthA convolutional neural network is a neural-network architecture that uses convolution and pooling operations to process structured spatial or grid-like data.
• 

  liveBookmanning.com
  Inside AIA convolutional neural network is a neural-network model that applies learned convolutional filters to structured data such as images.

Compare how 18 books explain convolutional neural network →

Related concepts

• language modelkind of · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
• 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.
• poolinguses · Pooling is an operation that aggregates values or representations across regions or axes to produce a reduced or summarized representation.
• convolution kerneluses · A convolution kernel is a small array or tensor of weights applied across local input regions to compute weighted responses and detect or transform patterns.
• U-Netincludes · U-Net is an encoder-decoder neural-network architecture with downsampling and upsampling paths connected by skip connections for combining features at multiple spatial scales.
• LeNetincludes · LeNet is an early convolutional neural-network architecture designed primarily for handwritten-digit and character recognition.

This explainer was generated by Manning's knowledge graph from the text of The AI Pocket Book. The section links point to the parts of the book it draws on.