Prehistory — From Neural Networks to the TransformerYann LeCun, Léon Bottou, Yoshua Bengio, Patrick HaffnerYann LeCunYoshua Bengio

Gradient-based learning applied to document recognition

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

Gradient-based learning applied to document recognition — presented LeNet-5 and MNIST

Why it matters

Established a practical CNN architecture combining convolution, pooling and fully connected layers, and made MNIST the standard testbed

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

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

Added in Week 35, 2026 · See that week

On the map — ⓪ Prehistory line

  1. Previous stopBackpropagation
  2. This record · stopGradient-based learning applied to document recognition
  3. Next stopNeural language model
See it on the map

Nearby on the same axis

Hochreiter and Schmidhuber publish Long Short-Term MemoryOfficialLearning long-term dependencies with gradient descent is difficultPressA Neural Probabilistic Language ModelPaperHochreiter's TU Munich thesis identifies the vanishing gradient problemPress