AI history

How did we get to today’s AI?

100 milestones · 1904 to today · each checked in at least 2 sources

AI methods: the milestones

36 milestones
Back to the timeline
AI methods

LeCun’s neural network reads handwritten zip codes

Yann LeCun and colleagues at Bell Labs trained a neural network with backpropagation to read handwritten zip codes from US mail. Its design built in knowledge about images, so one network handled the whole job.

Why it mattersIts design, later called a convolutional network, was used by several US banks to read handwritten cheques from the mid-1990s.

Note Fukushima’s neocognitron (1980) was a similar design. The new step was training such a network with backpropagation on real mail.

Built on
Who and what
  • Yann LeCun
  • John S. Denker
  • Lawrence D. Jackel
  • Bell Labs
  • US Postal Service
  • Convolutional networks
  • Handwriting recognition
We count only the page and your answer.Thank you. We counted only this page and your answer.
Next · LearnHow today’s AI models work: a short course

Checked 4 October 2026Corrections