Hinton, Osindero and Teh: fast learning for deep belief nets

What changed

Derived greedy layer-wise training for deep belief networks using restricted Boltzmann machines and complementary priors.

Scientific scope

The record is the exact three-author 2006 Neural Computation paper. It does not absorb earlier Boltzmann machines and wake–sleep, later deep-learning systems, or claim that its reported digit experiments establish general intelligence.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact three-author 2006 Neural Computation paper. It does not absorb earlier Boltzmann machines and wake–sleep, later deep-learning systems, or claim that its reported digit experiments establish general intelligence.

Contributors

• Geoffrey E. Hinton · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Simon Osindero · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Yee-Whye Teh · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• Hinton publication list for deep belief nets
• Author-hosted deep belief nets paper

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction