LeCun applies backprop-trained convolutional nets to handwritten digits (LeNet)
Yann LeCun and colleagues trained a convolutional neural network with backpropagation to read handwritten ZIP codes, the lineage that became LeNet-5 and was deployed to read cheques.
Key facts
- Paper: 'Backpropagation Applied to Handwritten Zip Code Recognition', Neural Computation 1(4), 1989
- Used weight sharing and local receptive fields (convolutions)
- LeNet-5 described in 'Gradient-based learning applied to document recognition' (Proc. IEEE, 1998)
- Introduced the MNIST dataset lineage used for decades
What happened
At Bell Labs, LeCun built convolutional networks trained end-to-end with backprop for digit recognition; later versions were used commercially to process a significant share of US cheques.
Why it matters
Convolutional networks became the backbone of computer vision and the architecture that triggered the deep learning revolution in 2012.
Changelog
- 2026-09-29: created
Related events
- Rumelhart, Hinton & Williams popularize backpropagation ★★★★★
- AlexNet wins ImageNet challenge, igniting the deep learning boom ★★★★★
Sources (3)
- paperBackpropagation Applied to Handwritten Zip Code Recognition (DOI)
- paperGradient-based learning applied to document recognition (1998, DOI)
- discussionWikipedia: LeNet
id: 1989-12-01-lecun-convolutional-networks · updated 2026-09-29 · open in the interactive timeline