articleTop 1% cited

Adaptive Mixtures of Local Experts

Neural Computation · 1991 · Vol. 3(1) · pp. 79–87

Robert A. Jacobs✉(Massachusetts Institute of Technology)Michael I. Jordan(Massachusetts Institute of Technology)Steven J. Nowlan(University of Toronto)Geoffrey E. Hinton(University of Toronto)

View via DOI Publisher page

Abstract

We present a new supervised learning procedure for systems composed of many separate networks, each of which learns to handle a subset of the complete set of training cases. The new procedure can be viewed either as a modular version of a multilayer supervised network, or as an associative version of competitive learning. It therefore provides a new link between these two apparently different approaches. We demonstrate that the learning procedure divides up a vowel discrimination task into appropriate subtasks, each of which can be solved by a very simple expert network.

Neural Networks and Applications Music and Audio Processing Speech and Audio ProcessingComputer scienceSimple (philosophy)Artificial intelligenceTask (project management)Set (abstract data type)Associative propertyMachine learningModular designArtificial neural networkCompetitive learning

Citations

4,795

FWCI

49.48

field-weighted impact

References

Percentile

100%

vs. same field & year

Citations per year

Cited by

A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition