Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

Spring 1991, Vol. 3, No. 1, Pages 79-87.
(doi: 10.1162/neco.1991.3.1.79)
© 1991 Massachusetts Institute of Technology
Adaptive Mixtures of Local Experts
Article PDF (433.58 KB)
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.