Self-organization in a two-layer CNN

被引：63

作者：

Arena, P ^{[1
]}

Baglio, S ^{[1
]}

Fortuna, L ^{[1
]}

Manganaro, G ^{[1
]}

机构：

[1] Univ Catania, Dipartimento Elettr Elettron & Sistemist, I-95125 Catania, Italy

来源：

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS | 1998年 / 45卷 / 02期

关键词：

cellular neural networks; nonlinear systems;

D O I：

10.1109/81.661681

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this brief, it is shown that a two-layer cellular neural network (CNN) with constant templates is suitable to generate self-organizing patterns and, therefore, it is able to model complex phenomena. The dynamic behavior of the single two-layer linear CNN cell is studied and the global behavior of the whole CNN is discussed. Different nonlinear phenomena are generated, including autowaves and spirals. Finally, the sensitivity with respect to parametric uncertainties and noise is investigated.

引用

页码：157 / 162

页数：6

共 21 条

[1]

[Anonymous], 1974, Differential Equations, Dynamical Systems, and Linear Algebra

[2] CELLULAR NEURAL NETWORKS - THEORY [J].