Rumelhart, Hinton & Williams popularize backpropagation
The Nature paper 'Learning representations by back-propagating errors' showed that multi-layer neural networks trained with backpropagation learn useful internal representations, reviving neural network research.
Key facts
- Published in Nature vol. 323, 9 October 1986
- Authors: David Rumelhart, Geoffrey Hinton, Ronald Williams
- Showed hidden units learn features not present in inputs
- Earlier related work includes Seppo Linnainmaa (1970) and Paul Werbos (1974)
What happened
The paper demonstrated gradient-based training of networks with hidden layers by propagating error derivatives backwards through the network.
Why it matters
Backpropagation is still how essentially all neural networks, including today's LLMs, are trained.
Changelog
- 2026-09-29: created
Related events
- Frank Rosenblatt's Perceptron — the first trainable neural network ★★★★★
- LeCun applies backprop-trained convolutional nets to handwritten digits (LeNet) ★★★★
- Hinton, LeCun and Bengio receive the Turing Award for deep learning ★★★
Sources (2)
- paperLearning representations by back-propagating errors (Nature, DOI)
- discussionWikipedia: Backpropagation
id: 1986-10-09-backpropagation · updated 2026-09-29 · open in the interactive timeline