LeNet

As explained in Distributed Machine Learning Patterns

LeNet is a convolutional neural network architecture originally designed for handwritten-digit recognition.

LeNet is a convolutional neural network for image classification, originally designed to recognize handwritten digits. Its architecture combines a convolutional encoder with two convolutional layers and a dense block with three fully connected layers. section 3.2.2

A simplified LeNet workflow includes:

• Process each video frame as a 28 × 28 image. section 3.2.2
• Learn feature mappings through convolutional and pooling layers. section 3.2.2
• Use fully connected layers to classify examples into one of ten selected entities. section 3.2.2

Figure 3.6 LeNet model architecture that could be used to classify new YouTube videos in 1 of 10 selected entities. (Source: Aston Zhang et al. Licensed under Creative Commons Attribution-ShareAlike 4.0 International Public License)

The architecture diagram shows how LeNet can classify new YouTube videos into one of ten selected entities. section 3.2.2

How Distributed Machine Learning Patterns covers it

How deep it goes

Explains the two-part architecture and input processing, but stops short of layer-specific dimensions or training procedures.

Examples

Uses handwritten-digit recognition and 28 × 28 video frames classified into ten selected entities.

What you can do after

Evaluate/understand a compact CNN architecture for image and frame classification.

How it connects

Connects convolutional neural networks with pooling layers, fully connected layers, backpropagation, and support vector machines.

liveBookmanning.com

Read Distributed Machine Learning Patterns on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Math and Architectures of Deep LearningA convolutional neural network architecture introduced for digit recognition and used here as the example image classifier.
• 

  liveBookmanning.com
  Machine Learning Algorithms in DepthLeNet is a convolutional neural network architecture designed for visual recognition tasks.

Compare how 3 books explain LeNet →

Related concepts

• convolutional neural networkkind of · A convolutional neural network is a neural-network architecture that applies learned convolutional operations to extract patterns from structured data.
• MNIST datasetuses · MNIST is a labeled dataset of 28-by-28-pixel grayscale images representing handwritten digits from zero through nine.
• classifieraddresses · A classifier is a predictive computational model that assigns inputs to one or more discrete classes or categories.
• convolutional layerpart of · A convolutional layer is a neural-network layer that applies shared learned filters to local regions of structured input to produce feature representations.
• PyTorchuses · PyTorch is an open-source machine-learning framework that provides tensor computation, automatic differentiation, and tools for developing and training neural networks.
• language modelkind of · A language model is a computational model that represents patterns in linguistic tokens to estimate their probabilities and predict or generate sequences of them.

This explainer was generated by Manning's knowledge graph from the text of Distributed Machine Learning Patterns. The section links point to the parts of the book it draws on.