Nonlinear gradient neural network for solving system of linear equations

DOI10.1016/j.ipl.2018.10.004zbMath1469.68012OpenAlexW2896377848WikidataQ129055607 ScholiaQ129055607MaRDI QIDQ1628684

Bolin Liao, Shuai Li, Zhijun Zhang, Long Jin, Lin Xiao, Ke Chen, Zhiguo Tan, KenLi Li

Publication date: 5 December 2018

Published in: Information Processing Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ipl.2018.10.004

zbMATH Keywords

performance evaluationfast convergencesystems of linear equationsgradient neural network (GNN)nonlinear activation function

Mathematics Subject Classification ID

Iterative numerical methods for linear systems (65F10) Networks and circuits as models of computation; circuit complexity (68Q06) Biologically inspired models of computation (DNA computing, membrane computing, etc.) (68Q07)

Related Items

A novel robust fixed-time convergent zeroing neural network for solving time-varying noise-polluted nonlinear equations ⋮ A robust fast convergence zeroing neural network and its applications to dynamic Sylvester equation solving and robot trajectory tracking ⋮ Robust zeroing neural network for fixed-time kinematic control of wheeled mobile robot in noise-polluted environment ⋮ Properties and computation of continuous-time solutions to linear systems ⋮ Gradient-based neural networks for solving periodic Sylvester matrix equations

Cites Work

• A finite-time recurrent neural network for solving online time-varying Sylvester matrix equation based on a new evolution formula
• 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
• Solving time-varying nonlinear inequalities using continuous and discrete-time Zhang dynamics
• A finite-time convergent dynamic system for solving online simultaneous linear equations
• Numerical and Symbolic Computations of Generalized Inverses
• A fully automated recurrent neural network for unknown dynamic system identification and control