计算机科学 ›› 2013, Vol. 40 ›› Issue (1): 262-265.

• 人工智能 • 上一篇    下一篇

基于二次型的CNN全局渐近稳定性研究

张小红,李德音   

  1. (江西理工大学信息工程学院 赣州341000)
  • 出版日期:2018-11-16 发布日期:2018-11-16

Research of Global Asymptotic Stability for CNN Based on Quadratic Form

  • Online:2018-11-16 Published:2018-11-16

摘要: 细胞神经网络稳定性目前已经在图像处理、视频通信和最优控制等领域得到了一定的应用,因此进行稳定性 的研究具有重要的意义,如何选择合理的参数模板是研究稳定性的关键问题。运用Lyapunov第二方法对细胞神经网 络的全局渐近稳定性进行分析,通过构造出一个较好的Lyapunov函数来得到判定系统全局渐近稳定的一组新的充分 条件。该条件改进了已有的结论,进一步推导和完善了系统全局渐近稳定平衡点为原点时的充分条件,经过数值仿真 实验验证了其有效性和可行性。

关键词: 细胞神经网络,全局渐近稳定,Lyapunov函数,二次型矩阵

Abstract: Stability of cellular neural networks is significant because it has been used in a certain application areas as im}r ge processing, video communication, optimal control and so on. How to choose a reasonable template of the parameters is the key issue of stability researches. Lyapunov second method was used to analyze the global asymptotic stability of cellular neural networks, and a better I_yapunov function was constructed to receive a new sufficient condition for deter- mining the global asymptotic stability of the system. The condition improves previous results and further derives a suffi- cicnt condition when original point is equilibrium point. Numerical simulations show their effectiveness and feasibility.

Key words: Cellular neural networks(CNN) , Global asymptotic stability, Lyapunov function, Quadratic form matrix

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!