...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Automatic Control >Varying-Parameter Convergent-Differential Neural Solution to Time-Varying Overdetermined System of Linear Equations
【24h】

Varying-Parameter Convergent-Differential Neural Solution to Time-Varying Overdetermined System of Linear Equations

机译：变化参数会聚差分神经解的线性方程的时变过量系统

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

To solve a time-varying overdetermined problem, a novel varying-parameter convergent-differential neural network (VP-CDNN) is proposed, designed, and discussed. Specifically, a vector-error function is first defined. Second, according to neural dynamic design method, an implicit-dynamic equation with a time-varying parameter is derived. Mathematics analysis and theoretical proof verify that the VP-CDNN can obtain the least-squares solution with a super exponential convergence rate. In addition, it is also proved that VP-CDNN can restrain the noise efficiently. Simulations among the VP-CDNN, gradient-based recurrent neural network and zeroing neural network verify that the VP-CDNN has faster speed, higher accuracy, and stronger robustness. At last, applications to data fitting and system identification further verify the high effectiveness and efficiency of the VP-CDNN.
机译：为了解决时变过定的问题，提出了一种新颖的改变参数会聚差分神经网络（VP-CDNN），设计和讨论。具体地，首先定义矢量错误功能。其次，根据神经动态设计方法，导出具有时变参数的隐式动态方程。数学分析和理论证明验证VP-CDNN可以以超级指数收敛速率获得最小二乘解。此外，还证明了VP-CDNN可以有效地抑制噪声。 VP-CDNN，基于梯度的复发性神经网络和归零神经网络之间的仿真验证了VP-CDNN的速度快，更高的精度和更强的鲁棒性。最后，应用于数据拟合和系统识别的应用进一步验证了VP-CDNN的高效率和效率。

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