Stability of discrete time recurrent neural networks and nonlinear optimization problems

DOI10.1016/J.NEUNET.2015.10.013MaRDI QIDQ1667540zbMATHOpenAlexWikidataFDO

Authors Jayant Singh, Nikita E. Barabanov

Publication date 30 August 2018

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1503.01818

zbMATH Keywords

optimizationLyapunov stabilityrecurrent neural network

Mathematics Subject Classification ID

Stability theory for difference equations (39A30) Applications of difference equations (39A60)

Abstract: We consider the method of Reduction of Dissipativity Domain to prove global Lyapunov stability of Discrete Time Recurrent Neural Networks. The standard and advanced criteria for Absolute Stability of these essentially nonlinear systems produce rather weak results. The method mentioned above is proved to be more powerful. It involves a multi-step procedure with maximization of special nonconvex functions over polytopes on every step. We derive conditions which guarantee an existence of at most one point of local maximum for such functions over every hyperplane. This nontrivial result is valid for wide range of neuron transfer functions.

Recommendations

• Local stability conditions for discrete-time cascade locally recurrent neural networks
• scientific article; zbMATH DE number 1307002
• Global exponential stability of discrete-time neural networks
• Global stability results of discrete recurrent neural networks with interval delays
• Robust exponential stability analysis of a larger class of discrete-time recurrent neural net\-works

Cites work

• scientific article; zbMATH DE number 4019532 (Why is no real title available?)
• scientific article; zbMATH DE number 3368525 (Why is no real title available?)
• scientific article; zbMATH DE number 3407506 (Why is no real title available?)
• scientific article; zbMATH DE number 3420573 (Why is no real title available?)
• scientific article; zbMATH DE number 3191450 (Why is no real title available?)
• A new method for stability analysis of nonlinear discrete-time systems
• Hermitian solutions of the discrete algebraic Riccati equation
• Image-processing algorithms realized by discrete-time cellular neural networks and their circuit implementations
• New Results on Stability of Discrete-Time Systems With Time-Varying State Delay
• On critical cases in the theory of absolute stability of controlled systems
• The stabilizing solution of the discrete algebraic riccati equation

Cited in

(11)

• On the stability properties of gated recurrent units neural networks
• Lur'e systems with multilayer perceptron and recurrent neural networks: absolute stability and dissipativity
• Local stability conditions for discrete-time cascade locally recurrent neural networks
• scientific article; zbMATH DE number 7113212 (Why is no real title available?)
• Four discrete-time ZD algorithms for dynamic linear matrix-vector inequality solving
• scientific article; zbMATH DE number 5951052 (Why is no real title available?)
• A critical case for the spiral stability for \(2\times 2\) discontinuous systems and an application to recursive neural networks
• Design and analysis of two discrete-time ZD algorithms for time-varying nonlinear minimization
• On the S-instability and degeneracy of discrete deep learning models
• Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions
• Delay-independent stability criteria for complex-valued BAM neutral-type neural networks with time delays

This page was built for publication: Stability of discrete time recurrent neural networks and nonlinear optimization problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1667540)