标题: Dynamics for discrete-time cellular neural networks
作者: Chen, SS
Shih, CW
应用数学系
Department of Applied Mathematics
关键字: cellular neural network;pattern formation;complete stability;homoclinic orbits;snap-back repeller;chaos
公开日期: 1-八月-2004
摘要: This presentation investigates the dynamics of discrete-time cellular neural networks (DT-CNN). In contrast to classical neural networks that are mostly gradient-like systems, DT-CNN possesses both complete stability and chaotic behaviours as different parameters are considered. An energy-like function which decreases along orbits of DT-CNN as well as the existence of a globally attracting set are derived. Complete stability can then be concluded, with further analysis on the sets on which the energy function is constant. The formations of saturated stationary patterns for DT-CNN are shown to be analogous to the ones in continuous-time CNN. Thus, DT-CNN shares similar properties with continuous-time CNN. By confirming the existence of snap-back repellers, hence transversal homoclinic orbits, we also conclude that DT-CNN with certain parameters exhibits chaotic dynamics, according to the theorem by Marotto.
URI: http://dx.doi.org/10.1142/S0218127404011053
http://hdl.handle.net/11536/26533
ISSN: 0218-1274
DOI: 10.1142/S0218127404011053
期刊: INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS
Volume: 14
Issue: 8
起始页: 2667
结束页: 2687
显示于类别:Articles


文件中的档案:

  1. 000224603300005.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.