首页    期刊浏览 2024年11月28日 星期四
登录注册

文章基本信息

  • 标题:Superior performance of using hyperbolic sine activation functions in ZNN illustrated via time-varying matrix square roots finding
  • 本地全文:下载
  • 作者:Zhang Yunong ; Jin Long ; Ke Zhende
  • 期刊名称:Computer Science and Information Systems
  • 印刷版ISSN:1820-0214
  • 电子版ISSN:2406-1018
  • 出版年度:2012
  • 卷号:9
  • 期号:4
  • 页码:1603-1625
  • DOI:10.2298/CSIS120121043Z
  • 出版社:ComSIS Consortium
  • 摘要:

    A special class of recurrent neural network (RNN), termed Zhang neural network (ZNN) depicted in the implicit dynamics, has recently been proposed for online solution of time-varying matrix square roots. Such a ZNN model can be constructed by using monotonically-increasing odd activation functions to obtain the theoretical time-varying matrix square roots in an error-free manner. Different choices of activation function arrays may lead to different performance of the ZNN model. Generally speaking, ZNN model using hyperbolic sine activation functions may achieve better performance, as compared with those using other activation functions. In this paper, to pursue the superior convergence and robustness properties, hyperbolic sine activation functions are applied to the ZNN model for online solution of time-varying matrix square roots. Theoretical analysis and computer-simulation results further demonstrate the superior performance of the ZNN model using hyperbolic sine activation functions in the context of large model-implementation errors, in comparison with that using linear activation functions.

  • 关键词:Zhang neural network; global exponential convergence; hyperbolic sine activation functions; time-varying matrix square roots; implementation errors
国家哲学社会科学文献中心版权所有