Convolutional neural network

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

A convolutional neural network is a neural network that processes structured inputs with learned convolutional filters, typically for tasks such as image classification.

A convolutional neural network (CNN) extends a deep-learning model with layers for localized feature extraction. It is typically used for 2D image processing, where it can improve classification and related tasks. CNNs are valuable but difficult to configure because layer type, size, placement, and hyperparameters interact. section 7.6 section 7.0

A practical CNN can be assembled as a Keras Sequential model: convolution layers extract features, max-pooling layers reduce the intermediate output, and Flatten plus Dense layers produce class outputs. For Fashion-MNIST, input images are normalized and reshaped from 2D arrays to 28×28×1 tensors so the channel dimension is explicit. section 7.1

Architecture choices require inspection rather than assuming a larger model is better:

• Compare model summaries to track output shapes and trainable parameter counts across convolution and pooling layers. section 7.1
• Watch training and validation results for memorization: a one-convolution-layer model can exceed 6 million parameters, fit reduced training data nearly perfectly, and perform poorly on validation data. section 7.1.1
• Use pooling and, where appropriate, batch normalization to alter model size and layer behavior; adding pooling in the demonstrated model reduces its parameter count to about one quarter. section 7.1.1

CNN architecture can also be searched through neuroevolution. Encode a variable-length sequence of convolution, pooling, batch-normalization, and dense-layer blocks, with values for filters or neurons and kernel sizes. A decoder reads those blocks and builds the Keras model; genetic operators can then optimize architectures for a dataset. section 7.2 section 7.6

A small Fashion-MNIST CNN

Start with 1,000 training and 100 test examples to keep repeated experiments tractable. Build three Conv2D layers with 64, 32, and 16 filters, place max pooling after each, then add Flatten, a 128-unit Dense layer, and a 10-output Dense layer. Inspect the resulting 23,728 trainable parameters before training. section 7.1

Figure 7.10 The gene encoding of CNN model architecture

Inspect the variable-length encoding to see how negative block identifiers separate CNN layer types from their hyperparameter values before decoding an architecture. section 7.2

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

How deep it goes

Walks through Keras construction, parameter summaries, training behavior, pooling effects, and gene-based architecture encoding.

Examples

Uses Fashion-MNIST, a three-convolution-layer Keras model, a oversized single-layer model, and variable-length gene sequences.

What you can do after

Build from scratch a Keras CNN and encode its layer architecture for genetic optimization.

How it connects

Connects convolutional neural networks with image classification, max pooling, batch normalization, generalization, genetic algorithms, and neuroevolution.

liveBookmanning.com

Read Evolutionary Deep Learning: Genetic algorithms and neural networks 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
  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
  The AI Pocket BookA neural network architecture that applies convolutions and downsampling to learn spatial features from grid-like data such as images.
• 

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