一种基于无源性理论的模糊Hopfield神经网络学习律设计方法
Passivity-based learning law design for a class of fuzzy Hopfield neural networks
摘要点击 57  全文点击 90  投稿时间:2018-09-13  修订日期:2019-03-26
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/CTA.2019.80699
  2020,37(2):405-410
中文关键词  模糊神经网络  无源性  学习律
英文关键词  Fuzzy neural networks  Passivity  Learning law
基金项目  
学科分类代码  
作者单位邮编
王婧 莱芜职业技术学院 271100
柏建军 杭州电子科技大学 310018
薛安克 杭州电子科技大学 
中文摘要
      本文研究了一类模糊Hopfield神经网络系统的稳定性问题。首先,基于无源性理论,设计了一种新的权重学习律,并通过构造的模糊Lyapunov函数证明了系统从输入到输出是无源的。在此基础上,证明了系统在该学习律下是输入到状态稳定的。相比于传统的公共Lypaunov函数,本文所提的模糊Lyapunov函数能保证系统具有更好的性能。最后,通过数值仿真验证了所提方法的有效性。
英文摘要
      The stability problem of a class of fuzzy Hopfield neural networks is investigated in this paper. Based on the passivity theory, a new learning law is proposed to guarantee the system to be input-to-output passive by constructing a new fuzzy Lyapunov function, which will allow the system a better performance compared to the common Lyapunov function. Then the system is proved to be input-to-state stable by using the new learning law. Finally, a numerical example is given to show the effectiveness of the proposed approach.