Finite iteration DT-CNN - new design and operating principles

Author

Merkwirth, C. ; Bröcker, J. ; Ogarzalek, M. ; Wichard, J.

Author_Institution

Computational Biol. & Appl. Algorithmics Group, Max-Planck-Inst. fur Informatik, Saarbrucken, Germany

Volume

5

fYear

2004

fDate

23-26 May 2004

Abstract

In this paper we propose to use the discrete-time cellular neural network (DT-CNN) in a finite iterate mode. In such a mode of operation no special requirements on template stability properties are needed. We propose a constructive back propagation based algorithm for template design. For a given number of iterations we can find optimal sequence of templates for a given problem to be solved. Our novel approach is demonstrated by a design of a digit recognition DT-CNN.

Keywords

backpropagation; cellular neural nets; discrete time systems; iterative methods; network synthesis; pattern recognition; constructive back propagation based algorithm; digit recognition DT-CNN; discrete-time cellular neural network; finite iteration DT-CNN; template design; template optimal sequence; template stability properties; Algorithm design and analysis; Cellular neural networks; Computational biology; Computer networks; Convergence; Design optimization; Electronic mail; Sequences; Stability; Steady-state;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2004. ISCAS '04. Proceedings of the 2004 International Symposium on

Print_ISBN

0-7803-8251-X

Type

conf

DOI

10.1109/ISCAS.2004.1329696

Filename

1329696