Switched exponential state estimation of neural networks based on passivity theory

Research output: Contribution to journalArticlepeer-review

76 Citations (Scopus)


In this paper, a new exponential state estimation method is proposed for switched Hopfield neural networks based on passivity theory. Through available output measurements, the main purpose is to estimate the neuron states such that the estimation error system is exponentially stable and passive from the control input to the output error. Based on augmented Lyapunov-Krasovskii functional, Jensen's inequality, and linear matrix inequality (LMI), a new delay-dependent state estimator for switched Hopfield neural networks can be achieved by solving LMIs, which can be easily facilitated by using some standard numerical packages. The unknown gain matrix is determined by solving delay-dependent LMIs. Finally, a numerical example is provided to demonstrate the effectiveness of the proposed method.

Original languageEnglish
Pages (from-to)573-586
Number of pages14
JournalNonlinear Dynamics
Issue number1
Publication statusPublished - 2012 Jan
Externally publishedYes


  • Augmented Lyapunov-Krasovskii functional
  • Linear matrix inequality (LMI)
  • Passivity theory
  • State estimation
  • Switched Hopfield neural networks

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Aerospace Engineering
  • Ocean Engineering
  • Mechanical Engineering
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Switched exponential state estimation of neural networks based on passivity theory'. Together they form a unique fingerprint.

Cite this