Deakin University
Browse

File(s) under permanent embargo

Non-functional regression: a new challenge for neural networks

journal contribution
posted on 2018-11-07, 00:00 authored by P Vamplew, Richard DazeleyRichard Dazeley, C Foale, T Choudhury
© 2018 Elsevier B.V. This work identifies an important, previously unaddressed issue for regression based on neural networks – learning to accurately approximate problems where the output is not a function of the input (i.e. where the number of outputs required varies across input space). Such non-functional regression problems arise in a number of applications, and can not be adequately handled by existing neural network algorithms. To demonstrate the benefits possible from directly addressing non-functional regression, this paper proposes the first neural algorithm to do so – an extension of the Resource Allocating Network (RAN) which adds additional output neurons to the network structure during training. This new algorithm, called the Resource Allocating Network with Varying Output Cardinality (RANVOC), is demonstrated to be capable of learning to perform non-functional regression, on both artificially constructed data and also on the real-world task of specifying parameter settings for a plasma-spray process. Importantly RANVOC is shown to outperform not just the original RAN algorithm, but also the best possible error rates achievable by any functional form of regression.

History

Journal

Neurocomputing

Volume

314

Pagination

326-335

Location

Amsterdam, The Netherlands

ISSN

0925-2312

eISSN

1872-8286

Language

eng

Publication classification

C Journal article, C1 Refereed article in a scholarly journal

Copyright notice

2018, Elsevier

Publisher

Elsevier

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC