...
首页> 外文期刊>Neural Networks, IEEE Transactions on >Analysis and Design of a -Winners-Take-All Model With a Single State Variable and the Heaviside Step Activation Function
【24h】

Analysis and Design of a -Winners-Take-All Model With a Single State Variable and the Heaviside Step Activation Function

机译:具有单状态变量和重步激活函数的“赢家通吃”模型的分析和设计

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       

摘要

This paper presents a $k$-winners-take-all $(k{rm WTA})$ neural network with a single state variable and a hard-limiting activation function. First, following several $k{rm WTA}$ problem formulations, related existing $k{rm WTA}$ networks are reviewed. Then, the $k{rm WTA}$ model model with a single state variable and a Heaviside step activation function is described and its global stability and finite-time convergence are proven with derived upper and lower bounds. In addition, the initial state estimation and a discrete-time version of the $k{rm WTA}$ model are discussed. Furthermore, two selected applications to parallel sorting and rank-order filtering based on the $k{rm WTA}$ model are discussed. Finally, simulation results show the effectiveness and performance of the $k{rm WTA}$ model.
机译:本文提出了一个具有单个状态变量和硬限制激活函数的$ k $赢家通吃的$(k {rm WTA})$神经网络。首先,遵循几种$ k {rm WTA} $的问题公式,对相关的现有$ k {rm WTA} $网络进行审查。然后,描述了具有单个状态变量和Heaviside阶跃激活函数的$ k {rm WTA} $模型模型,并通过导出的上下界证明了其全局稳定性和有限时间收敛性。此外,还讨论了$ k {rm WTA} $模型的初始状态估计和离散时间版本。此外,还讨论了基于$ k {rm WTA} $模型的两个并行筛选和排序过滤应用程序。最后,仿真结果显示了$ k {rm WTA} $模型的有效性和性能。

著录项

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