Robust stability of a class of neural networks with time delays

DOI10.1007/BF02219053MaRDI QIDQ1363324zbMATH OpenOpenAlexFDO

Authors V. L. Kharitonov, Andrew D. B. Paice

Publication date 10 March 1998

Published in Journal of Dynamics and Differential Equations (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/bf02219053

zbMATH Keywords

linear dominancelocal stabilityroots of quasipolynomialssensitivity to parameter changes

Mathematics Subject Classification ID

Nonlinear ordinary differential equations and systems (34A34) Neural networks for/in biological studies, artificial life and related topics (92B20)

Review text

Neural networks are modelled by nonlinear ODE's with one or two constant delays. It is assumed that the linear part, centred on a static equilibrium, is dominant. The stability analysis is carried out by examining the eigenvalues (roots of quasipolynomials), and their dependence on parameters. The permissible change of the latter determines ``robustness. This notion does not coincide with an analoguos notion introduced by Andronov and extended by Smale. The stability so determined is local. The possibility of small ``hard-type self-oscillations is not considered.

Recommendations

• scientific article; zbMATH DE number 5269010
• A note on the robust stability of neural networks with time delay
• scientific article; zbMATH DE number 500989
• Robust stability analysis of static neural network with S-type distributed delays
• Advances in Neural Networks – ISNN 2005

Cites work

• Differential-difference equations
• Finiteness results for sigmoidal “neural” networks
• scientific article; zbMATH DE number 4207939 (Why is no real title available?)
• scientific article; zbMATH DE number 5050658 (Why is no real title available?)
• Neurons with graded response have collective computational properties like those of two-state neurons
• On the zeros of some transcendental functions
• Robust stability for time-delay systems: the edge theorem and graphical tests
• Robust stability of time-delay systems
• Root locations of an entire polytope of polynomials: It suffices to check the edges
• Stability in a model of a delayed neural network
• The complex structured singular value

Cited in

(7)

• Robust stability of impulsive switched neural networks with multiple time delays
• A note on the robust stability of neural networks with time delay
• scientific article; zbMATH DE number 5951942 (Why is no real title available?)
• scientific article; zbMATH DE number 5707672 (Why is no real title available?)
• Qualitative analysis of a neural network model with multiple time delays
• scientific article; zbMATH DE number 1545015 (Why is no real title available?)
• scientific article; zbMATH DE number 5269010 (Why is no real title available?)

This page was built for publication: Robust stability of a class of neural networks with time delays

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1363324)