General recurrent neural network for solving generalized linear matrix equation

DOI10.1155/2017/9063762MaRDI QIDQ1674941zbMATH OpenOpenAlexWikidataFDO

Authors Zhan Li, Hong Cheng, Hongliang Guo

Publication date 26 October 2017

Published in Complexity (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1155/2017/9063762

zbMATH Keywords

generalized linear matrix equationglobal convergencenonlinear recurrent neural network

Mathematics Subject Classification ID

Matrix equations and identities (15A24) Neural networks for/in biological studies, artificial life and related topics (92B20) Nonlinear systems in control theory (93C10)

Review text

Summary: This brief proposes a general framework of the nonlinear recurrent neural network for solving online the generalized linear matrix equation (GLME) with global convergence property. If the linear activation function is utilized, the neural state matrix of the nonlinear recurrent neural network can globally and exponentially converge to the unique theoretical solution of GLME. Additionally, as compared with the case of using the linear activation function, two specific types of nonlinear activation functions are proposed for the general nonlinear recurrent neural network model to achieve superior convergence. Illustrative examples are shown to demonstrate the efficacy of the general nonlinear recurrent neural network model and its superior convergence when activated by the aforementioned nonlinear activation functions.

Recommendations

• Nonlinear recurrent neural networks for finite-time solution of general time-varying linear matrix equations
• Recurrent neural networks for solving linear matrix equations
• Recurrent Neural Network for Computing Outer Inverse
• Gradient-based neural networks for solving periodic Sylvester matrix equations
• Comparison on neural solvers for the Lyapunov matrix equation with stationary image nonstationary coefficients

Cites work

• A new solution to the generalized Sylvester matrix equation \(AV-EVF=BW\)
• Bounds in algebraic Riccati and Lyapunov equations: a survey and some new results
• Efficient solution of linear matrix equations with application to multistatic antenna array processing
• Gradient based iterative algorithms for solving a class of matrix equations
• Gradient based iterative solutions for general linear matrix equations
• Improved neural dynamics for online Sylvester equations solving
• Improved neural solution for the Lyapunov matrix equation based on gradient search
• Iterative least-squares solutions of coupled sylvester matrix equations
• Lagrange programming neural networks
• Neural networks and physical systems with emergent collective computational abilities
• New estimates for solutions of Lyapunov equations
• On the generalized Sylvester mapping and matrix equations
• Recurrent neural networks for solving linear matrix equations

Cited in

(4)

• Recurrent neural networks for solving linear matrix equations
• Nonlinear recurrent neural networks for finite-time solution of general time-varying linear matrix equations
• Eigen solution of neural networks and its application in prediction and analysis of controller parameters of grinding robot in complex environments
• Nonlinear function activated GNN versus ZNN for online solution of general linear matrix equations

This page was built for publication: General recurrent neural network for solving generalized linear matrix equation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1674941)