Convolutional neural network

As explained in Sutskever's List

A convolutional neural network is a neural network architecture that applies learned convolutional filters to structured input such as images.

In 2012, AlexNet made convolutional neural networks (CNNs) difficult to dismiss. Trained by Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton to classify images, it achieved a 15% top-5 error rate in the ImageNet competition, against roughly 26% for conventional methods. Top-5 error means the correct answer is absent from a model’s five leading guesses. section 2.0

A CNN is a neural network that applies learned convolutional filters to structured input such as images. Where earlier vision systems relied on handcrafted features, AlexNet was trained end-to-end on raw images. Its success showed that a different architecture could extract more from image data—not merely that a larger dataset would improve an established approach. section 1.1 section 2.5.5

From an unlikely entrant to the default approach

AlexNet was the only artificial neural network in the 2012 ImageNet competition. In 2013, nearly every entry used a CNN. Subsequent architectures pushed error lower: GoogLeNet reached 6.7% top-5 error in 2014, and R-CNN extended CNNs to object detection. section 2.5.5

Figure 2.6 The top-5 error rates in the ILSVRC from 2010 to 2017. SIFT and SVM won in 2010 and 2011, but performance plateaued. CNNs won from 2012 to 2017, including AlexNet in 2012, and eventually saturated the benchmark.

The competition results show the plateau before AlexNet, successive CNN victories, and the benchmark’s eventual saturation. section 2.5.5

Convolution also appeared in sequence models. ByteNet and ConvS2S used dilated convolutions to widen the context available to local filters, but convolutional networks still relied on fixed, local interactions. The Transformer offered a contrasting approach: self-attention rather than convolution to connect information within a sequence. A decisive architecture for image recognition was therefore not the last word on how to model context. section 5.8

How Sutskever's List covers it

How deep it goes

Explains CNNs through competition results, end-to-end learning, and local interactions, without detailing filter implementation.

Examples

Compares AlexNet’s 15% top-5 error with conventional methods’ roughly 26%, then traces GoogLeNet and R-CNN.

What it assumes

Recaps artificial neural networks, handcrafted feature engineering, and the training difficulties that preceded AlexNet.

What you can do after

Evaluate/understand why AlexNet displaced handcrafted image classifiers and why local interactions constrained convolutional sequence models.

How it connects

Connects CNNs to handcrafted features, ImageNet, object detection, dilated convolutions, recurrent neural networks, and self-attention.

liveBookmanning.com

Read Sutskever's List 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
  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
  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 Sutskever's List. The section links point to the parts of the book it draws on.