Passivity Analysis of a General Form of Recurrent Neural Network with Multiple Delays

Authors:
Jinhua Huang;Jiqing Liu
Affiliations:
Department of Electric and Electronic Engineering, Wuhan Institute of Shipbuilding Technology, Wuhan, China 430050;Department of Electric and Electronic Engineering, Wuhan Institute of Shipbuilding Technology, Wuhan, China 430050
Venue:
ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part III
Year:
2009

Citing 10
Cited 0

CMAC neural networks for control of nonlinear dynamical systems: structure, stability and passivity

Automatica (Journal of IFAC)
Dissipative Systems Analysis and Control: Theory and Applications

Dissipative Systems Analysis and Control: Theory and Applications
Criteria for exponential stability of Cohen-Grossberg neural networks

Neural Networks
Global exponential stability of recurrent neural networks with time-varying delays in the presence of strong external stimuli

Neural Networks
Letters: Passivity analysis of integro-differential neural networks with time-varying delays

Neurocomputing
Analysis and Design of Associative Memories Based on Recurrent Neural Networks with Linear Saturation Activation Functions and Time-Varying Delays

Neural Computation
Some new results on system identification with dynamic neural networks

IEEE Transactions on Neural Networks
Robust global exponential stability of Cohen-Grossberg neural networks with time delays

IEEE Transactions on Neural Networks
Improved conditions for global exponential stability of recurrent neural networks with time-varying delays

IEEE Transactions on Neural Networks
Multiperiodicity of Discrete-Time Delayed Neural Networks Evoked by Periodic External Inputs

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, by using some analytic techniques, several sufficient conditions are given to ensure the passivity of a general form of recurrent neural network with multiple delays. The passivity conditions are presented in terms of a negative semi-definite matrix declared. They are easily verifiable and easier to check computing with some conditions in terms of complicated linear matrix inequality.