The NNSYSID toolbox-a MATLAB(R) toolbox for system identification with neural networks

Author

Norgaard, M. ; Ravn, O. ; Hansen, L.K. ; Poulsen, N.K.

Author_Institution

Dept. of Autom., Tech. Univ., Lyngby, Denmark

fYear

1996

Firstpage

374

Lastpage

379

Abstract

To assist the identification of nonlinear dynamic systems, a set of tools has been developed for the MATLAB(R) environment. The tools include a number of different model structures, highly effective training algorithms, functions for validating trained networks, and pruning algorithms for determination of optimal network architectures. The toolbox should be regarded as a nonlinear extension to the system identification toolbox provided by The MathWorks, Inc. This paper gives a brief overview of the entire collection of toolbox functions

Keywords

control system analysis computing; identification; learning (artificial intelligence); multilayer perceptrons; nonlinear dynamical systems; MATLAB toolbox; MathWorks; NNSYSID toolbox; model structures; multilayer perceptron; neural networks; nonlinear dynamic systems; pruning algorithms; system identification; training algorithm; Automation; Buildings; Computer languages; MATLAB; Mathematical model; Multi-layer neural network; Neural networks; Nonlinear dynamical systems; Power system modeling; System identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Aided Control System Design, 1996., Proceedings of the 1996 IEEE International Symposium on

Conference_Location

Dearborn, MI

Print_ISBN

0-7803-3032-3

Type

conf

DOI

10.1109/CACSD.1996.555321

Filename

555321