The learning dynamics of a universal approximator

Research output: Contribution to journalArticle

View graph of relations Save citation

Authors

Research units

Abstract

The learning properties of a universal approximator, a normalized committee machine with adjustable biases, are studied for on-line back-propagation learning. Within a statistical mechanics framework, numerical studies show that this model has features which do not exist in previously studied two-layer network models without adjustable biases, e.g., attractive suboptimal symmetric phases even for realizable cases and noiseless data.

Documents

  • Advances.pdf

    Rights statement: Copyright of the Massachusetts Institute of Technology Press (MIT Press)

    786 KB, PDF-document

Details

Original languageEnglish
Pages (from-to)288-294
Number of pages7
JournalAdvances in Neural Information Processing Systems
Volume9
StatePublished - May 1997

Bibliographic note

Copyright of the Massachusetts Institute of Technology Press (MIT Press)

    Keywords

  • approximator, back-propagation, symmetric phases, realizable cases, noiseless data

Download statistics

No data available

Employable Graduates; Exploitable Research

Copy the text from this field...