Prediction- and simulation-error based perceptron training: Solution space analysis and a novel combined training scheme

Patrick Connally, Kang Li, George Irwin

Research output: Contribution to journalArticlepeer-review

20 Citations (Scopus)

Abstract

Previous papers have noted the difficulty in obtaining neural models which are stable under simulation when trained using prediction-error-based methods. Here the differences between series-parallel and parallel identification structures for training neural models are investigated. The effect of the error surface shape on training convergence and simulation performance is analysed using a standard algorithm operating in both training modes. A combined series-parallel/parallel training scheme is proposed, aiming to provide a more effective means of obtaining accurate neural simulation models. Simulation examples show the combined scheme is advantageous in circumstances where the solution space is known or suspected to be complex. (c) 2006 Elsevier B.V. All rights reserved.
Original languageEnglish
Pages (from-to)819-827
Number of pages9
JournalNeurocomputing
Volume70
Issue number4-6
DOIs
Publication statusPublished - Jan 2007

ASJC Scopus subject areas

  • Artificial Intelligence
  • Cellular and Molecular Neuroscience

Fingerprint

Dive into the research topics of 'Prediction- and simulation-error based perceptron training: Solution space analysis and a novel combined training scheme'. Together they form a unique fingerprint.

Cite this