• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Multiple and Complete Stability of Recurrent Neural Networks With Sinusoidal Activation Function
【24h】

Multiple and Complete Stability of Recurrent Neural Networks With Sinusoidal Activation Function

机译：具有正弦激活功能的经常性神经网络的多和完全稳定性

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This article presents new theoretical results on multistability and complete stability of recurrent neural networks with a sinusoidal activation function. Sufficient criteria are provided for ascertaining the stability of recurrent neural networks with various numbers of equilibria, such as a unique equilibrium, finite, and countably infinite numbers of equilibria. Multiple exponential stability criteria of equilibria are derived, and the attraction basins of equilibria are estimated. Furthermore, criteria for complete stability and instability of equilibria are derived for recurrent neural networks without time delay. In contrast to the existing stability results with a finite number of equilibria, the new criteria, herein, are applicable for both finite and countably infinite numbers of equilibria. Two illustrative examples with finite and countably infinite numbers of equilibria are elaborated to substantiate the results.
机译：本文介绍了具有正弦激活功能的多重性和经常性神经网络的完全稳定性的新理论结果。提供足够的标准，用于确定具有各种数量的均衡的经常性神经网络的稳定性，例如独特的平衡，有限，有限的无限均衡。估计均衡的多重指数稳定性标准，估计均衡的吸引力盆地。此外，由于经常性神经网络导出了完全稳定性和均衡的不稳定性的标准，而无需延迟。与具有有限数量的均衡的现有稳定性结果相比，本文的新标准适用于有限且可以是无限的均衡。阐述了具有有限和可计数无限均衡的两个说明性实例以证实结果。

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