Estimation of the basin of attractions of stable equilibrium points in CNNs

Author

Mladenov, Valeri M. ; Leenaerts, Domine M W

Author_Institution

Dept. of Theor. Electrotech., Tech. Univ. Sofia, Bulgaria

fYear

1998

fDate

14-17 Apr 1998

Firstpage

62

Lastpage

67

Abstract

We present an approach to estimate the basin of attraction of stable equilibrium points in cellular neural networks (CNNs). The approach is based on the determination of the so called tree of regions connected with each stable equilibrium points described in our previous work (1997). The new contribution is connected with additional separation of the regions where the boundaries between different basins are located. The suggested separation with internal hyperplanes will help to estimate more precisely the boundaries between different basins, because the previous algorithm to obtain the trees could not give the exact description of the basin of attractions

Keywords

cellular neural nets; nonlinear differential equations; nonlinear dynamical systems; stability; trees (mathematics); attraction basin; boundaries; cellular neural networks; nonlinear differential equations; nonlinear dynamical systems; region trees; stable equilibrium points; Books; Cellular neural networks; Convergence; Hopfield neural networks; Linearity; Lyapunov method; Neural networks; Nonlinear dynamical systems; Piecewise linear techniques; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Cellular Neural Networks and Their Applications Proceedings, 1998 Fifth IEEE International Workshop on

Conference_Location

London

Print_ISBN

0-7803-4867-2

Type

conf

DOI

10.1109/CNNA.1998.685331

Filename

685331