Parameter identification via neural networks with fast convergence

N. Yadaiah, L. Sivakumar and B.L. Deekshatulu

Mathematics and Computers in Simulation (MATCOM), 2000, vol. 51, issue 3, 157-167

Abstract: The parameter identification using artificial neural networks is becoming very popular. In this chapter, the parameters of dynamical system are identified using artificial neural networks. A fast gradient decent technique for the parameter identification of a linear dynamical system has been presented. The following concepts are used for training of neural networks while identifying the system parameters: (1) batch wise training of neural networks; (2) variable learning parameter and; (3) an intelligent check over the rate at which parameters are converging. The complete algorithm is summarized as a flow chart. A detailed mathematical formulation is given. The simulation results and a comparative study with existing method is included.

Keywords: Artificial neural networks; Parameter identification; Optimization; Supervised learning; Performance index. (search for similar items in EconPapers)
Date: 2000
References: View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0378475499001147
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:matcom:v:51:y:2000:i:3:p:157-167

Access Statistics for this article

Mathematics and Computers in Simulation (MATCOM) is currently edited by Robert Beauwens

More articles in Mathematics and Computers in Simulation (MATCOM) from Elsevier
Bibliographic data for series maintained by Catherine Liu ().