首页> 外文期刊>International Journal of Adaptive Control and Signal Processing >Input-to-state H_∞ learning of recurrent neural networks with delay and disturbance
【24h】

Input-to-state H_∞ learning of recurrent neural networks with delay and disturbance

机译:具有延迟与扰动的反复性神经网络的输入到状态H_∞学习

获取原文
获取原文并翻译 | 示例
           

摘要

This article deals with the issue of input-to-state Script capital H-infinity stabilization for recurrent neural networks with delay and external disturbance. The goal is to design a suitable weight-learning law to make the considered network input-to-state stable with a predefined Script capital L-2-gain. Based on the solution of linear matrix inequalities, two schemes for the desired learning law are presented via using decay-rate-dependent and decay-rate-independent Lyapunov functionals, respectively. It is shown that, in the absence of external disturbance, the proposed learning law also guarantees the exponential stability of the network. To illustrate the applicability of the present weight-learning law, two numerical examples with simulations are given.
机译:本文涉及具有延迟和外部干扰的经常性神经网络的输入到州脚本资本H-Infinity稳定问题。 目标是设计合适的权力学习法,以使所考虑的网络输入到状态稳定,具有预定义的脚本资本L-2增益。 基于线性矩阵不等式的解决方案,通过使用衰减率依赖和无关的Lyapunov函数来呈现所需学习法的两种方案。 结果表明,在没有外部干扰的情况下,建议的学习法也保证了网络的指数稳定性。 为了说明本权力学习法的适用性,给出了具有模拟的两个数值例子。

著录项

  • 来源
  • 作者单位

    Anhui Univ Technol Sch Comp Sci & Technol Maanshan 243032 Peoples R China;

    Anhui Univ Technol Sch Comp Sci & Technol Maanshan 243032 Peoples R China;

    Anhui Univ Technol Sch Comp Sci & Technol Maanshan 243032 Peoples R China|Anhui Univ Technol Res Inst Informat Technol Maanshan Peoples R China;

    Anhui Univ Technol Sch Comp Sci & Technol Maanshan 243032 Peoples R China|Anhui Univ Technol Res Inst Informat Technol Maanshan Peoples R China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);美国《生物学医学文摘》(MEDLINE);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    L-2-gain; delay; input-to-state stability; recurrent neural networks; weight learning;

    机译:L-2-GAIN;延迟;输入到状态稳定;经常性神经网络;体重学习;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号