Global exponential convergence of recurrent neural networks with variable delays

Authors:
Zhang Yi
Affiliations:
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, People's Republic of China
Venue:
Theoretical Computer Science
Year:
2004

Citing 6
Cited 6

Stability in asymmetric Hopfield nets with transmission delays

Physica D
Results concerning the absolute stability of delayed neural networks

Neural Networks
Multistability analysis for recurrent neural networks with unsaturating piecewise linear transfer functions

Neural Computation
Robust stability for interval Hopfield neural networks with time delay

IEEE Transactions on Neural Networks
Estimate of exponential convergence rate and exponential stability for neural networks

IEEE Transactions on Neural Networks
Neurocomputing with time delay analysis for solving convex quadratic programming problems

IEEE Transactions on Neural Networks

Absolute exponential stability of a class of recurrent neural networks with multiple and variable delays

Theoretical Computer Science
Fundamental study: Global dynamics for non-autonomous reaction-diffusion neural networks with time-varying delays

Theoretical Computer Science
Global Exponential Stability and Periodicity of CNNs with Time-Varying Discrete and Distributed Delays

ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
Exponential dissipativity of non-autonomous neural networks with distributed delays and reaction-diffusion terms

ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Universal approach to study delayed dynamical systems

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part I
Original article: Attracting and invariant sets of non-autonomous reaction-diffusion neural networks with time-varying delays

Mathematics and Computers in Simulation

Quantified Score

Hi-index	5.23

Visualization

Abstract

Convergence analysis of recurrent neural networks is an important research direction in the field of neural networks. Novel methods to study the global exponential convergence of recurrent neural networks with variable delays are proposed. A condition for global exponential stability, which is independent of the delays, is derived by the method of delayed inequalities analysis. Another condition for global exponential stability, which depends on the delays, is obtained via the method of constructing a suitable and interesting Lyapunov functional.