An automated hammerstein recurrent neural network for dynamic applications

Yen Ping Chen, Jeen-Shing Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This paper presents an automated Hammerstein recurrent neural network (HRNN) associated with a self-construction learning algorithm capable of building the network with a compact state-space representation from the input-output measurements of dynamic systems. The proposed HRNN is constituted by two connectionist networks - a static nonlinear network cascaded with a linear dynamic network. The self-construction algorithm is devised to automate the HRNN construction process via three mechanisms: an order determination scheme, a weight initialization method, and a parameter optimization method. With the learning algorithm, trial and error on the selection of network sizes or parameter initialization can be totally exempted. Computer simulations on nonlinear dynamic system identification validate that the proposed HRNN can closely capture the dynamical behavior of the unknown system with a compact network size.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Computational Intelligence
Pages193-198
Number of pages6
Publication statusPublished - 2005 Dec 1
EventIASTED International Conference on Computational Intelligence - Calgary, AB, Canada
Duration: 2005 Jul 42005 Jul 6

Publication series

NameProceedings of the IASTED International Conference on Computational Intelligence
Volume2005

Other

OtherIASTED International Conference on Computational Intelligence
Country/TerritoryCanada
CityCalgary, AB
Period05-07-0405-07-06

All Science Journal Classification (ASJC) codes

  • General Engineering

Fingerprint

Dive into the research topics of 'An automated hammerstein recurrent neural network for dynamic applications'. Together they form a unique fingerprint.

Cite this