bluelogo.gif (1643 bytes)

home page
people
research
publications
seminars
travel
search
UCL

Adaptive Mixtures of Local Experts

Robert Jacobs, Michael Jordan
Department of Brain and Cognitive Sciences
MIT, Cambridge, MA, USA

Steven Nowlan, Geoffrey Hinton
Department of Computer Science
University of Toronto & University of Toronto
Toronto, Canada

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 networks, 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.

 Download [ps] [pdf]

[home page]  [publications]