---
id: "2006-07-01-deep-belief-networks"
url: "https://postcutoff.com/e/2006-07-01-deep-belief-networks/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2006-07-01"
date_precision: month
category: research
importance: 4
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/2006-07-01-deep-belief-networks/

# Hinton's deep belief nets launch the 'deep learning' revival

Hinton, Osindero and Teh showed that deep networks could be trained effectively with greedy layer-wise pretraining, a result widely credited with reviving interest in 'deep learning'.

## Key facts
- Paper: 'A Fast Learning Algorithm for Deep Belief Nets', Neural Computation 18(7), July 2006
- Companion Science paper on autoencoders (Hinton & Salakhutdinov, 2006)
- Stacked restricted Boltzmann machines trained one layer at a time
- Research funded in part by CIFAR

## What happened

Researchers demonstrated a practical method to train many-layer networks, achieving strong results on MNIST.

## Why it matters

It rebranded neural networks as 'deep learning' and set the stage for the GPU-powered breakthroughs of 2009–2012.

## 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. [A Fast Learning Algorithm for Deep Belief Nets (DOI)](https://doi.org/10.1162/neco.2006.18.7.1527) (doi.org, paper)
2. [Wikipedia: Deep belief network](https://en.wikipedia.org/wiki/Deep_belief_network) (en.wikipedia.org, discussion)

## Changes

- 2026-09-29 (filed): Created

## Related

- People: [Geoffrey Hinton](https://postcutoff.com/person/geoffrey-hinton/)