A learning algorithm for cellular neural networks (CNN) solving nonlinear partial differential equations

Author

Puffer, F. ; Tetzlaff, R. ; Wolf, D.

Author_Institution

Inst. fur Angewandte Phys., Frankfurt Univ., Germany

fYear

1995

Firstpage

501

Lastpage

504

Abstract

A learning procedure for CNN is presented and applied in order to find the parameters of networks approximating the dynamics of certain nonlinear systems which are characterized by partial differential equations (PDE). Our results show that - depending on the training pattern - solutions of various PDE can be approximated with high accuracy by a simple CNN structure. Results for two nonlinear PDE, Burgers´ equation and the Korteweg-de Vries equation, are discussed in detail

Keywords

Korteweg-de Vries equation; cellular neural nets; learning (artificial intelligence); nonlinear differential equations; partial differential equations; Burgers´ equation; Korteweg-de Vries equation; cellular neural networks; learning algorithm; nonlinear partial differential equations; Artificial neural networks; Backpropagation; Cellular neural networks; Differential equations; Learning systems; Neurofeedback; Nonlinear equations; Nonlinear systems; Partial differential equations; Piecewise linear approximation;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems, and Electronics, 1995. ISSSE '95, Proceedings., 1995 URSI International Symposium on

Conference_Location

San Francisco

Print_ISBN

0-7803-2516-8

Type

conf

DOI

10.1109/ISSSE.1995.498041

Filename

498041