A NEURAL NETWORK BASED IDENTIFICATION FOR COMPLEX NON-LINEAR SYSTEMS

 

Otu Vaarmann

 

Abstract

 

This report treats numerical methods for highly non-linear least squares problems for which procedural and rounding error are unavoidable, e.g. those arising in the development of various non-linear system identification techniques based on input-output representation of the model such as training of artificial neural networks. Let F be a Frechet-differentiable operator acting between Hilbert spaces H1 and H2 and such that the range of its first derivative is not necessarily closed. For solving the equation F(x)=0 or minimizing the functional , two-parameter iterative regularization methods based on the Gauss-Newton method are developed under certain conditions on a test function and the required solution . Their computational aspects are discussed and a local convergence theorem is proposed.

 

Lecture Notes in Management Science (2011) Vol. 3: 39-46

3rd International Conference on Applied Operational Research, Proceedings

© Tadbir Operational Research Group Ltd. All rights reserved.

www.tadbir.ca

 

ISSN 2008-0050 (Print)

ISSN 1927-0097 (Online)

 

ARTICLE OUTLINE

 

·         Introduction

·         Methods And Convergence Theorem

·         Concluding Remarks

·         References

 

Full Text PDF