WRSWorld Research StateContribute
WORLD RESEARCH STATE

Hinton, Dayan, Frey and Neal: the wake–sleep algorithm

Contribution grade

Neural and deep learning · ALGORITHM

Reference score100,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Introduced a wake–sleep learning procedure that alternately adapts bottom-up recognition connections and top-down generative connections in multilayer neural networks.

Scientific scope

The record is the exact 1995 Science paper. Helmholtz-machine framing, later variational inference, variational autoencoders and subsequent generative-model training methods remain separate.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact 1995 Science paper. Helmholtz-machine framing, later variational inference, variational autoencoders and subsequent generative-model training methods remain separate.

Contributors

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