Ackley, Hinton and Sejnowski: a learning algorithm for Boltzmann machines

What changed

Introduced a stochastic parallel-network learning rule derived from statistical-mechanical search, adjusting connection strengths so that the network learns internal representations of task constraints.

Scientific scope

The record is the exact 1985 Cognitive Science paper. Hopfield networks, simulated annealing, later restricted Boltzmann machines, deep belief networks and modern energy-based models 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 1985 Cognitive Science paper. Hopfield networks, simulated annealing, later restricted Boltzmann machines, deep belief networks and modern energy-based models remain separate.

Contributors

• David H. Ackley · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Geoffrey E. Hinton · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Terrence J. Sejnowski · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• Wiley record for the Boltzmann-machine learning algorithm
• Author-hosted Boltzmann-machine 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