AWhat changed
Introduced a supervised modular learning procedure in which a gating network allocates cases among expert networks and learning localizes weight changes to the experts responsible for each subtask.
Scientific scope
The record is the exact 1991 Neural Computation paper. Earlier presentations, later hierarchical mixtures, probabilistic mixture-of-experts models, ensemble methods and transformer mixture-of-experts systems 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 1991 Neural Computation paper. Earlier presentations, later hierarchical mixtures, probabilistic mixture-of-experts models, ensemble methods and transformer mixture-of-experts systems remain separate.
Contributors
- Robert A. Jacobs · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Michael I. Jordan · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Steven J. Nowlan · 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.
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