Title :
A Study on Convergence of Competitive CNNs
Author :
Di Marco, M. ; Forti, M. ; Grazzini, M. ; Nistri, P. ; Pancioni, L.
Author_Institution :
Dept. of Inf. Eng., Siena Univ.
Abstract :
In a series of papers published in the seventies, Grossberg has developed a geometric approach for analyzing the global dynamical behavior and convergence properties of a class of competitive dynamical systems. In this paper, Grossberg approach is extended to competitive standard cellular neural networks (CNNs), and it is used to investigate convergence of classes of non-symmetric competitive CNNs under the hypothesis that they induce a globally consistent decision scheme.
Keywords :
cellular neural nets; convergence; directed graphs; nonlinear differential equations; competitive cellular neural networks; competitive dynamical systems; convergence properties; geometric approach; global dynamical behavior; globally consistent decision scheme; Cellular neural networks; Convergence; Differential equations; Information analysis; Lyapunov method; Neurons; Piecewise linear techniques; Voting;
Conference_Titel :
Circuits and Systems, 2007. ISCAS 2007. IEEE International Symposium on
Conference_Location :
New Orleans, LA
Print_ISBN :
1-4244-0920-9
Electronic_ISBN :
1-4244-0921-7
DOI :
10.1109/ISCAS.2007.378100
