Dynamics for discrete-time cellular neural networks
檔案
- 000224603300005.pdf (1.81 MB, Adobe PDF)
日期
2004-08-01
類型
系所
期刊名稱
INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS
卷期與頁次
第 14 卷第 8 期,頁 2667–2687
ISSN
0218-1274
語言
英文
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.