Authors:
Adrian–Mihail Stoica
1
and
Isaac Yaesh
2
Affiliations:
1
Faculty of Aerospace Engineering, University ”Politehnica” of Bucharest, Romania
;
2
IMI Advanced Systems Div., Israel
Keyword(s):
Chaos, Stochastic systems, Hopfield Neural Networks, Recurrent Neural Networks, Sprocedure, Linear matrix inequalities, Direct Adaptive Control.
Related
Ontology
Subjects/Areas/Topics:
Adaptive Signal Processing and Control
;
Hybrid Dynamical Systems
;
Informatics in Control, Automation and Robotics
;
Nonlinear Signals and Systems
;
Signal Processing, Sensors, Systems Modeling and Control
Abstract:
The paper presents passivity conditions for a class of stochastic Hopfield neural networks with state–dependent noise and with Markovian jumps. The contributions are mainly based on the stability analysis of the considered class of stochastic neural networks using infinitesimal generators of appropriate stochastic Lyapunov–type functions. The derived passivity conditions are expressed in terms of the solutions of some specific systems of linear matrix inequalities. The theoretical results are illustrated by a simplified adaptive control problem for a dynamic system with chaotic behavior.