Accelerating a recurrent neural network to finite-time convergence using a new design formula and its application to time-varying matrix square root

DOI10.1016/j.jfranklin.2017.06.012zbMath1395.93353OpenAlexW2728677037MaRDI QIDQ1661241

Lin Xiao

Publication date: 16 August 2018

Published in: Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jfranklin.2017.06.012

zbMATH Keywords

finite-time convergencedesign formularecurrent neural network accelerationtime-varying matrix square root

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Design techniques (robust design, computer-aided design, etc.) (93B51) Discrete-time control/observation systems (93C55)

Related Items (16)

Simulation of varying parameter recurrent neural network with application to matrix inversion ⋮ A family of varying-parameter finite-time zeroing neural networks for solving time-varying Sylvester equation and its application ⋮ Nonlinear recurrent neural networks for finite-time solution of general time-varying linear matrix equations ⋮ Design, verification and robotic application of a novel recurrent neural network for computing dynamic Sylvester equation ⋮ Proposing, developing and verification of a novel discrete-time zeroing neural network for solving future augmented Sylvester matrix equation ⋮ Discrete gradient-zeroing neural network algorithms for handling future quadratic program as well as robot arm via ten-instant formula ⋮ A novel finite-time complex-valued zeoring neural network for solving time-varying complex-valued Sylvester equation ⋮ A new ZNN model for finding discrete time-variant matrix square root: from model design to parameter analysis ⋮ A modified noise-tolerant ZNN model for solving time-varying Sylvester equation with its application to robot manipulator ⋮ Solving time-varying linear inequalities by finite-time convergent zeroing neural networks ⋮ Event-triggered zeroing dynamics for motion control of Stewart platform ⋮ Solving future equation systems using integral-type error function and using twice ZNN formula with disturbances suppressed ⋮ Adaptive coefficient designs for nonlinear activation function and its application to zeroing neural network for solving time-varying Sylvester equation ⋮ Design and analysis of robust nonlinear neural dynamics for solving dynamic nonlinear equation within finite time ⋮ Finite-time convergent zeroing neural network for solving time-varying algebraic Riccati equations ⋮ General 9-instant discrete-time Zhang neural network for time-dependent applications

Cites Work

• A note on square roots of nonnegative matrices
• Finite-time consensus of second-order multi-agent systems via auxiliary system approach
• A new design formula exploited for accelerating Zhang neural network and its application to time-varying matrix inversion
• On square roots and norms of matrices with symmetry properties
• On exponential convergence of nonlinear gradient dynamics system with application to square root finding
• Stable iterations for the matrix square root
• Time-varying square roots finding via Zhang dynamics versus gradient dynamics and the former's link and new explanation to Newton-Raphson iteration
• \(\mathcal H_\infty\) state estimation for memristive neural networks with time-varying delays: the discrete-time case
• Zeroing Dynamics, Gradient Dynamics, and Newton Iterations
• Uniqueness of matrix square roots and an application

This page was built for publication: Accelerating a recurrent neural network to finite-time convergence using a new design formula and its application to time-varying matrix square root