---
id: "1986-10-09-backpropagation"
url: "https://postcutoff.com/e/1986-10-09-backpropagation/"
as_of: "2026-11-13T13:49:00+01:00"
date: "1986-10-09"
date_precision: day
category: research
importance: 5
confidence: high
status: [Confirmed]
sources: 2
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/1986-10-09-backpropagation/

# 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.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [Learning representations by back-propagating errors (Nature, DOI)](https://doi.org/10.1038/323533a0) (doi.org, paper)
2. [Wikipedia: Backpropagation](https://en.wikipedia.org/wiki/Backpropagation) (en.wikipedia.org, discussion)

## Changes

- 2026-09-29 (filed): Created

## Related

- 1989-12-01: [LeCun applies backprop-trained convolutional nets to handwritten digits](https://postcutoff.com/e/1989-12-01-lecun-convolutional-networks/index.md)
- 1958-07-01: [Frank Rosenblatt's Perceptron, the first trainable neural network](https://postcutoff.com/e/1958-07-01-perceptron/index.md)
- People: [Geoffrey Hinton](https://postcutoff.com/person/geoffrey-hinton/)