An on-line hybrid learning algorithm for multilayer perceptron in identification problems

Daohang Sha, Vladimir Bajic

Research output: Contribution to journalArticlepeer-review

16 Scopus citations

Abstract

A hybrid learning algorithm for multilayered perceptrons (MLPs) and pattern-by-pattern training, based on optimized instantaneous learning rates and the recursive least squares method, is proposed. This hybrid solution is developed for on-line identification of process models based on the use of MLPs, and can speed up the learning process of the MLPs substantially, while simultaneously preserving the stability of the learning process. For illustration and test purposes the proposed algorithm is applied to the identification of a non-linear dynamic system.

Original languageEnglish (US)
Pages (from-to)587-598
Number of pages12
JournalComputers and Electrical Engineering
Volume28
Issue number6
DOIs
StatePublished - Nov 1 2002

Keywords

  • Gradient descent method
  • Hybrid learning
  • Neural networks
  • Recursive least squares parameter estimation
  • Soft computing

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'An on-line hybrid learning algorithm for multilayer perceptron in identification problems'. Together they form a unique fingerprint.

Cite this