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

Research output: Contribution to conferences › Paper › Contributed › peer-review

Contributors

  • F. Puffer - , University Hospital Frankfurt (Author)
  • R. Tetzlaff - , University Hospital Frankfurt (Author)
  • Dietrich Wolf - , University Hospital Frankfurt (Author)

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.

Details

Original languageEnglish
Pages501-504
Number of pages4
Publication statusPublished - 1995
Peer-reviewedYes
Externally publishedYes

Conference

TitleProceedings of the 1995 3rd URSI International Symposium on Signals, Systems and Electronics, ISSSE'95
Duration25 - 27 October 1995
CitySan Francisco, CA, USA

External IDs

ORCID /0000-0001-7436-0103/work/142240248

Keywords

ASJC Scopus subject areas