Backpropagation Applied to Handwritten Zip Code Recognition

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Backpropagation Applied to Handwritten Zip Code Recognition — applied a convolutional neural network trained with backpropagation to zip code recognition

Why it matters

An early case of combining weight sharing with backpropagation to apply a neural network to a real-world task

Source — Primary sources first; secondary reports are labelled “Press”

Pressen.wikipedia.orghttps://en.wikipedia.org/wiki/Convolutional_neural_network

Added in Week 35, 2026 · See that week

On the map — ⓪ Prehistory line

  1. Previous stopBackpropagation
  2. This recordBackpropagation Applied to Handwritten Zip Code Recognition
  3. Next stopGradient-based learning applied to document recognition
See it on the map

Nearby on the same axis

Approximation by superpositions of a sigmoidal functionPaperMultilayer feedforward networks are universal approximatorsPressHochreiter's TU Munich thesis identifies the vanishing gradient problemPressLearning representations by back-propagating errorsPaper