Design of a nonlinearly activated gradient-based neural network and its application to matrix inversion

DOI10.2298/FIL2015095ZMaRDI QIDQ5082441FDOQ5082441

Authors:

Publication date: 16 June 2022

Published in: Filomat (Search for Journal in Brave)

Recommendations

• Global exponential convergence and stability of gradient-based neural network for online matrix inversion
• Neural network approach to computing matrix inversion
• A recurrent neural network for real-time matrix inversion
• Improved neural solution for the Lyapunov matrix equation based on gradient search
• Nonlinear gradient neural network for solving system of linear equations

zbMATH Keywords

matrix inversionsimulation verificationnonlinear activation functiongradient-based neural network

Mathematics Subject Classification ID

Theory of matrix inversion and generalized inverses (15A09)

Cites Work

• A recurrent neural network for real-time matrix inversion
• From Zhang Neural Network to Newton Iteration for Matrix Inversion
• Finite iterative algorithms for extended Sylvester-conjugate matrix equations
• A new design formula exploited for accelerating Zhang neural network and its application to time-varying matrix inversion
• Global exponential convergence and stability of gradient-based neural network for online matrix inversion
• Nonlinear recurrent neural networks for finite-time solution of general time-varying linear matrix equations
• Two New Types of Zhang Neural Networks Solving Systems of Time-Varying Nonlinear Inequalities
• A class of finite-time dual neural networks for solving quadratic programming problems and its \(k\)-winners-take-all application
• Regularized image reconstruction using SVD and a neural network method for matrix inversion
• A finite-time recurrent neural network for solving online time-varying Sylvester matrix equation based on a new evolution formula
• Design, verification and robotic application of a novel recurrent neural network for computing dynamic Sylvester equation
• Noise-Tolerant ZNN Models for Solving Time-Varying Zero-Finding Problems: A Control-Theoretic Approach

Cited In (2)

• The pseudo-inverse matrix and its application in the improved BP neural network
• Global exponential convergence and stability of gradient-based neural network for online matrix inversion

This page was built for publication: Design of a nonlinearly activated gradient-based neural network and its application to matrix inversion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5082441)