A universal approximation theorem for mixture-of-experts models

Nguyen, Hien D., Lloyd-Jones, Luke R. and McLachlan, Geoffrey J. (2016) A universal approximation theorem for mixture-of-experts models. Neural Computation, 28 12: 2585-2593. doi:10.1162/NECO_a_00892

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
UQ416303_OA.pdf application/pdf Bytes 0

Author Nguyen, Hien D.
Lloyd-Jones, Luke R.
McLachlan, Geoffrey J.
Title A universal approximation theorem for mixture-of-experts models
Journal name Neural Computation   Check publisher's open access policy
ISSN 0899-7667
Publication date 2016-12-01
Year available 2016
Sub-type Article (original research)
DOI 10.1162/NECO_a_00892
Open Access Status File (Publisher version)
Volume 28
Issue 12
Start page 2585
End page 2593
Total pages 9
Place of publication Cambridge, MA United States
Publisher MIT Press
Language eng
Abstract The mixture-of-experts (MoE) model is a popular neural network architecture for nonlinear regression and classification. The class of MoE mean functions is known to be uniformly convergent to any unknown target function, assuming that the target function is from a Sobolev space that is sufficiently differentiable and that the domain of estimation is a compact unit hypercube. We provide an alternative result, which shows that the class of MoE mean functions is dense in the class of all continuous functions over arbitrary compact domains of estimation. Our result can be viewed as a universal approximation theorem for MoE models. The theorem we present allows MoE users to be confident in applying such models for estimation when data arise from nonlinear and nondifferentiable generative processes.
Keyword Computer Science, Artificial Intelligence
Computer Science
Neurosciences & Neurology
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: School of Mathematics and Physics
HERDC Pre-Audit
Centre for Neurogenetics and Statistical Genomics Publications
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 3 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Sun, 01 Jan 2017, 10:16:49 EST by System User on behalf of School of Mathematics & Physics