Improved neural solution for the Lyapunov matrix equation based on gradient search

详细信息    查看全文

• 作者：Yuhuan Chen ; Chenfu Yi ; Dengyu Qiao
• 关键词：Analysis of algorithms ; Recurrent neural networks ; Gradient search ; Hierarchical identification principle ; Energy function ; Activation function
• 刊名：Information Processing Letters
• 出版年：2013
• 出版时间：November-December, 2013
• 年：2013
• 卷：113
• 期：22-24
• 页码：876-881
• 全文大小：762 K

文摘

By using the hierarchical identification principle, based on the conventional gradient search, two neural subsystems are developed and investigated for the online solution of the well-known Lyapunov matrix equation. Theoretical analysis shows that, by using any monotonically-increasing odd activation function, the gradient-based neural networks (GNN) can solve the Lyapunov equation exactly and efficiently. Computer simulation results confirm that the solution of the presented GNN models could globally converge to the solution of the Lyapunov matrix equation. Moreover, when using the power-sigmoid activation functions, the GNN models have superior convergence when compared to linear models.